{"install":"Install","market":"via dsh-market · recommended","marketHint":"copy the market install command","cli":"via CLI","copy":"copy install","copyLabel":"Copy install command","dlTitle":"Downloads (30d)","items":[{"cat":"model","tag":"Models & Providers","dl":25519,"stars":562,"added":"2026-08-30","npm":1,"name":"dsh-connect-workbuddy","owner":"dingminhua","short":"dsh-connect-workbuddy","slug":"dingminhua/dsh-connect-workbuddy","desc":"Connects locally signed-in WorkBuddy models to DSH, supports per-model image input opt-in, account switching, and a read-only credits overview with daily check-in.","cmd":"dsh plugin --profile web add dsh-connect-workbuddy","href":"/p/dingminhua/dsh-connect-workbuddy/"},{"cat":"model","tag":"Models & Providers","dl":23352,"stars":259,"added":"2026-08-16","npm":1,"name":"dsh-codex-subscription","owner":"WSL043","short":"dsh-codex-subscription","slug":"WSL043/dsh-codex-subscription","desc":"ChatGPT OAuth provider for Codex models with subscription web search, quota and safe reset, image tools, Fast mode, and model-aware context; no API key or Codex CLI.","cmd":"dsh plugin --profile web add dsh-codex-subscription","href":"/p/WSL043/dsh-codex-subscription/"},{"cat":"model","tag":"Models & Providers","dl":21635,"stars":13,"added":"2026-08-23","npm":1,"name":"dsh-thinking-levels","owner":"drscrewdriver","short":"dsh-thinking-levels","slug":"drscrewdriver/dsh-thinking-levels","desc":"Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.","cmd":"dsh plugin --profile web add dsh-thinking-levels","href":"/p/drscrewdriver/dsh-thinking-levels/"},{"cat":"model","tag":"Models & Providers","dl":14361,"stars":310,"added":"2026-09-13","npm":1,"name":"dsh-deepseek-web-login","owner":"cv-superding","short":"dsh-deepseek-web-login","slug":"cv-superding/dsh-deepseek-web-login","desc":"Adds a deepseek-web provider that uses chat.deepseek.com web models in DSH, with browser login capture, PoW request signing, SSE streaming, and prompting-based tool calls.","cmd":"dsh plugin --profile web add dsh-deepseek-web-login","href":"/p/cv-superding/dsh-deepseek-web-login/"},{"cat":"model","tag":"Models & Providers","dl":13267,"stars":433,"added":"2026-08-15","npm":1,"name":"dsh-commandcode-provider","owner":"Mars-Sea","short":"dsh-commandcode-provider","slug":"Mars-Sea/dsh-commandcode-provider","desc":"Unofficial Command Code LLM provider: registers a `commandcode` route with a live model catalog and reasoning-effort support.","cmd":"dsh plugin --profile web add @mars-sea/dsh-commandcode-provider","href":"/p/Mars-Sea/dsh-commandcode-provider/"},{"cat":"model","tag":"Models & Providers","dl":11856,"stars":16,"added":"2026-08-28","npm":1,"name":"dsh-subscriptions","owner":"GooDAnDReaDY","short":"dsh-subscriptions","slug":"GooDAnDReaDY/dsh-subscriptions","desc":"Registers ChatGPT Codex, Claude, Grok and Antigravity subscriptions as DeepSeek Harness LLM providers through OAuth, so no API key is needed for them.","cmd":"dsh plugin --profile web add @goodandready/dsh-subscriptions","href":"/p/GooDAnDReaDY/dsh-subscriptions/"},{"cat":"model","tag":"Models & Providers","dl":11761,"stars":159,"added":"2026-08-30","npm":1,"name":"dsh-connect-trae","owner":"dingminhua","short":"dsh-connect-trae","slug":"dingminhua/dsh-connect-trae","desc":"Connects locally signed-in Trae CN models to DSH, supports DSH-executed tool calls, account switching, and Work/general credit visibility.","cmd":"dsh plugin --profile web add dsh-connect-trae","href":"/p/dingminhua/dsh-connect-trae/"},{"cat":"model","tag":"Models & Providers","dl":11154,"stars":342,"added":"2026-08-30","npm":1,"name":"opencode2dsh","owner":"FishBottle7","short":"opencode2dsh","slug":"FishBottle7/opencode2dsh--packages-plugin","desc":"Exposes OpenCode Zen free models to DeepSeek Harness, with no API key.","cmd":"dsh plugin --profile web add @opencode2dsh/dsh-plugin","href":"/p/FishBottle7/opencode2dsh--packages-plugin/"},{"cat":"model","tag":"Models & Providers","dl":10169,"stars":165,"added":"2026-08-14","npm":1,"name":"dsh-codex-connect","owner":"franksong2702","short":"dsh-codex-connect","slug":"franksong2702/dsh-codex-connect","desc":"Connect ChatGPT OAuth and OpenAI Codex models to DeepSeek Harness, with opt-in search and image tools.","cmd":"dsh plugin --profile web add dsh-codex-connect","href":"/p/franksong2702/dsh-codex-connect/"},{"cat":"model","tag":"Models & Providers","dl":9308,"stars":504,"added":"2026-08-21","npm":1,"name":"dsh-plugin-subscriptions","owner":"V1ki","short":"dsh-plugin-subscriptions","slug":"V1ki/dsh-plugin-subscriptions","desc":"Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.","cmd":"dsh plugin --profile web add dsh-plugin-subscriptions","href":"/p/V1ki/dsh-plugin-subscriptions/"},{"cat":"model","tag":"Models & Providers","dl":9203,"stars":10,"added":"2026-08-28","npm":1,"name":"dsh-key-rotation","owner":"GooDAnDReaDY","short":"dsh-key-rotation","slug":"GooDAnDReaDY/dsh-key-rotation","desc":"Keeps a pool of API keys per provider with auto-created clone routes, switches to the next key on quota or rate-limit errors, probes cooled keys for recovery, and exposes the pools, cooldown and switch codes in a Settings section.","cmd":"dsh plugin --profile web add @goodandready/dsh-key-rotation","href":"/p/GooDAnDReaDY/dsh-key-rotation/"},{"cat":"model","tag":"Models & Providers","dl":7996,"stars":8,"added":"2026-09-05","npm":1,"name":"dsh-clinebot","owner":"GooDAnDReaDY","short":"dsh-clinebot","slug":"GooDAnDReaDY/dsh-clinebot","desc":"ClineBot and ClinePass integration for DeepSeek Harness: dedicated settings page, live quota dashboard, in-UI key saving, curated and custom model selection, and a /cline command.","cmd":"dsh plugin --profile web add @goodandready/dsh-clinebot","href":"/p/GooDAnDReaDY/dsh-clinebot/"},{"cat":"model","tag":"Models & Providers","dl":6961,"stars":182,"added":"2026-09-18","npm":1,"name":"dsh-opencode-go","owner":"Duskriver","short":"dsh-opencode-go","slug":"Duskriver/dsh-opencode-go","desc":"OpenCode Go provider with live gateway model discovery, online models.dev capability metadata, session routing, and Web settings with subscription usage.","cmd":"dsh plugin --profile web add dsh-opencode-go","href":"/p/Duskriver/dsh-opencode-go/"},{"cat":"model","tag":"Models & Providers","dl":6847,"stars":56,"added":"2026-08-20","npm":1,"name":"dsh-thinking-effort","owner":"hytime","short":"dsh-thinking-effort","slug":"hytime/dsh-thinking-effort","desc":"Configure reasoning-effort levels and sub-agent defaults for custom DSH models.","cmd":"dsh plugin --profile web add @hytime/dsh-thinking-effort","href":"/p/hytime/dsh-thinking-effort/"},{"cat":"model","tag":"Models & Providers","dl":5856,"stars":23,"added":"2026-08-13","npm":1,"name":"dsh-llm-fallbacks","owner":"omdsh-dev","short":"dsh-llm-fallbacks","slug":"omdsh-dev/dsh-llm-fallbacks","desc":"Role-based LLM retry & fallback strategies.","cmd":"dsh plugin --profile web add dsh-llm-fallbacks","href":"/p/omdsh-dev/dsh-llm-fallbacks/"},{"cat":"model","tag":"Models & Providers","dl":5734,"stars":0,"added":"2026-08-22","npm":1,"name":"dsh-plugins#qwen-token-plan-cn-responses","owner":"nickhelion","short":"dsh-plugins#qwen-token-plan-cn-responses","slug":"nickhelion/dsh-plugins--packages-qwen-token-plan-cn-responses","desc":"Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, with Qwen server-side tools, DSH local function tools, text/reasoning/tool-call multi-turn history, persisted image attachments, and a per-release official model catalog snapshot.","cmd":"dsh plugin --profile web add dsh-qwen-token-plan-cn-responses","href":"/p/nickhelion/dsh-plugins--packages-qwen-token-plan-cn-responses/"},{"cat":"model","tag":"Models & Providers","dl":5020,"stars":123,"added":"2026-08-20","npm":1,"name":"dsh-agy-link","owner":"amlyczz","short":"dsh-agy-link","slug":"amlyczz/dsh-agy-link","desc":"Google Antigravity (agy CLI) models for DSH — streaming chat with Gemini/Claude/GPT-OSS subscriptions, native tool cards, thinking turns, and in-GUI Google OAuth login.","cmd":"dsh plugin --profile web add dsh-agy-link","href":"/p/amlyczz/dsh-agy-link/"},{"cat":"model","tag":"Models & Providers","dl":4998,"stars":2,"added":"2026-09-18","npm":1,"name":"dsh-model-router","owner":"Neptune810","short":"dsh-model-router","slug":"Neptune810/dsh-model-router","desc":"Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.","cmd":"dsh plugin --profile web add @neptune810/dsh-model-router","href":"/p/Neptune810/dsh-model-router/"},{"cat":"model","tag":"Models & Providers","dl":4663,"stars":65,"added":"2026-08-23","npm":1,"name":"dsh-better-reasoning-effort","owner":"HaoyueQin","short":"dsh-better-reasoning-effort","slug":"HaoyueQin/dsh-better-reasoning-effort","desc":"Per-model reasoning-effort and input-modality configuration for third-party providers: suggestions fused from a model knowledge base and raw /models endpoint evidence with confidence labels, edited inside the official Models page card.","cmd":"dsh plugin --profile web add dsh-better-reasoning-effort","href":"/p/HaoyueQin/dsh-better-reasoning-effort/"},{"cat":"model","tag":"Models & Providers","dl":4576,"stars":2,"added":"2026-09-20","npm":1,"name":"dsh-llm-hub","owner":"webkubor","short":"dsh-llm-hub","slug":"webkubor/dsh-llm-hub","desc":"Fills in what the official pi-ai adapter leaves out on the Models page: gateway reachability probing with latency, one-click pull of the gateway model catalog with checkbox write-back into settings, DeepSeek balance and provider quota shown in place, the protocol and endpoint each provider is actually wired to, and a model dropdown that lists only what works right now — a dead key, an empty balance or an exhausted quota is hidden until you fix it, and comes back on its own.","cmd":"dsh plugin --profile web add @dsh-plugins/dsh-llm-hub","href":"/p/webkubor/dsh-llm-hub/"},{"cat":"model","tag":"Models & Providers","dl":4234,"stars":372,"added":"2026-10-21","npm":1,"name":"dsh-model-router","owner":"Alice-Marx","short":"dsh-model-router","slug":"Alice-Marx/dsh-model-router","desc":"Routes DeepSeek Harness work across configured model APIs and supported vendor CLIs with dependency-aware packages and cost previews.","cmd":"dsh plugin --profile web add @ljwei-stak/dsh-model-router","href":"/p/Alice-Marx/dsh-model-router/"},{"cat":"model","tag":"Models & Providers","dl":4194,"stars":6,"added":"2026-08-28","npm":1,"name":"dsh-model-sync","owner":"GooDAnDReaDY","short":"dsh-model-sync","slug":"GooDAnDReaDY/dsh-model-sync","desc":"Synchronizes the model catalog of API-key providers from the provider itself instead of maintaining the model list by hand.","cmd":"dsh plugin --profile web add @goodandready/dsh-model-sync","href":"/p/GooDAnDReaDY/dsh-model-sync/"},{"cat":"model","tag":"Models & Providers","dl":3869,"stars":21,"added":"2026-08-29","npm":1,"name":"dsh-local-ai","owner":"PerryLink","short":"dsh-local-ai","slug":"PerryLink/dsh-local-ai","desc":"Ollama provider for DeepSeek Harness with model management, health checks, rule-based local routing, and cloud fallback.","cmd":"dsh plugin --profile web add dsh-local-ai","href":"/p/PerryLink/dsh-local-ai/"},{"cat":"model","tag":"Models & Providers","dl":3736,"stars":1,"added":"2026-09-13","npm":1,"name":"dsh-autotier","owner":"PerryLink","short":"dsh-autotier","slug":"PerryLink/dsh-autotier","desc":"Automatic model-tier routing for DeepSeek Harness: one user instruction enters, one tier decision comes out — complex intent is planned on the strong tier and implemented on the cheap tier, simple intent stays cheap throughout, with a deterministic guard and a TTL escalation fallback.","cmd":"dsh plugin --profile web add dsh-autotier","href":"/p/PerryLink/dsh-autotier/"},{"cat":"model","tag":"Models & Providers","dl":3656,"stars":21,"added":"2026-08-17","npm":1,"name":"dsh-plugin-subagent-director","owner":"SeverusZh","short":"dsh-plugin-subagent-director","slug":"SeverusZh/dsh-plugin-subagent-director","desc":"Per-subagent LLM provider/model selection with role templates.","cmd":"dsh plugin --profile web add dsh-plugin-subagent-director","href":"/p/SeverusZh/dsh-plugin-subagent-director/"},{"cat":"model","tag":"Models & Providers","dl":3611,"stars":9,"added":"2026-09-29","npm":1,"name":"dsh-connect-qoder","owner":"eghrhegpe","short":"dsh-connect-qoder","slug":"eghrhegpe/dsh-connect-qoder","desc":"Registers Qoder CN and international language models into DSH, fetching each model's rate automatically as it shifts with off-peak hours. It also provides a daily check-in, a usage pill and a credit lookup. Needs the Qoder login state on this machine, or one browser login.","cmd":"dsh plugin --profile web add @eghrhegpe/dsh-connect-qoder","href":"/p/eghrhegpe/dsh-connect-qoder/"},{"cat":"model","tag":"Models & Providers","dl":3556,"stars":1,"added":"2026-10-19","npm":1,"name":"dsh-copilot-auth","owner":"iasiv5","short":"dsh-copilot-auth","slug":"iasiv5/dsh-copilot-auth","desc":"Adds a web device-code sign-in and sign-out entry for the built-in GitHub Copilot provider in DSH, presets an out-of-the-box Copilot provider route, keeps credentials in the built-in credential store, and manages the model catalog as a first-login fallback that never overwrites customized model entries.","cmd":"dsh plugin --profile web add @inventec/dsh-copilot-auth","href":"/p/iasiv5/dsh-copilot-auth/"},{"cat":"model","tag":"Models & Providers","dl":3535,"stars":11,"added":"2026-10-17","npm":1,"name":"dsh-plugin-chatgpt","owner":"ckanner","short":"dsh-plugin-chatgpt","slug":"ckanner/dsh-plugin-chatgpt","desc":"Signs in to a ChatGPT account over OAuth and serves that plan's models as a DeepSeek Harness provider route, calling api.openai.com/v1/responses with the account's plan scope rather than the Codex backend.","cmd":"dsh plugin --profile web add dsh-plugin-chatgpt","href":"/p/ckanner/dsh-plugin-chatgpt/"},{"cat":"model","tag":"Models & Providers","dl":3532,"stars":5,"added":"2026-10-12","npm":1,"name":"dsh-connect-sensenova-token-plan","owner":"eghrhegpe","short":"dsh-connect-sensenova-token-plan","slug":"eghrhegpe/dsh-connect-sensenova-token-plan","desc":"One-tap connect SenseNova Token Plan language and image models into DSH (off by default), with image recognition and thinking level filled in automatically. On a rate limit it backs off and retries on its own instead of misreading it as an exhausted quota. After signing in to the SenseNova console you can see the usage pill, credit pools and per-model consumption. Xiaohuanxiong can also be signed in by QR code, bringing in its models and their consumption multipliers, and taking over DSH web search.","cmd":"dsh plugin --profile web add dsh-connect-sensenova-token-plan","href":"/p/eghrhegpe/dsh-connect-sensenova-token-plan/"},{"cat":"model","tag":"Models & Providers","dl":3406,"stars":12,"added":"2026-09-19","npm":1,"name":"dsh-tool-antigravity","owner":"Jaylor-Wang","short":"dsh-tool-antigravity","slug":"Jaylor-Wang/dsh-tool-antigravity","desc":"Connect Google Antigravity Code Assist OAuth accounts to DeepSeek Harness for Gemini and Claude streaming LLM routing and Nano Banana 2 image generation.","cmd":"dsh plugin --profile web add dsh-tool-antigravity","href":"/p/Jaylor-Wang/dsh-tool-antigravity/"},{"cat":"model","tag":"Models & Providers","dl":3366,"stars":15,"added":"2026-08-30","npm":1,"name":"dsh-router","owner":"CARVIN94","short":"dsh-router","slug":"CARVIN94/dsh-router","desc":"An AI routing gateway that runs as a DSH plugin. Adds a Routing System sidebar panel for suppliers, account pool, fallback combos and API keys, and serves an OpenAI-compatible endpoint at http://localhost:3080/v1.","cmd":"dsh plugin --profile web add dsh-router-core","href":"/p/CARVIN94/dsh-router/"},{"cat":"model","tag":"Models & Providers","dl":3251,"stars":11,"added":"2026-08-18","npm":1,"name":"dsh-subagent-default-model#plugin","owner":"dingminhua","short":"dsh-subagent-default-model#plugin","slug":"dingminhua/dsh-subagent-default-model--plugin","desc":"Configurable default model for subagent delegations via settings.yaml, with single-model and multi-model round-robin or random strategies.","cmd":"dsh plugin --profile web add dsh-subagent-default-model","href":"/p/dingminhua/dsh-subagent-default-model--plugin/"},{"cat":"model","tag":"Models & Providers","dl":3219,"stars":6,"added":"2026-08-25","npm":1,"name":"dsh-grok-kit","owner":"MaRi23333","short":"dsh-grok-kit","slug":"MaRi23333/dsh-grok-kit","desc":"Unofficial Grok integration for eligible X Subscription, SuperGrok, or X Premium accounts: shared Grok CLI OAuth, chat with optional main-loop web/X search, and experimental image generation, image editing, and video generation (all media features disabled by default).","cmd":"dsh plugin --profile web add dsh-grok-kit","href":"/p/MaRi23333/dsh-grok-kit/"},{"cat":"model","tag":"Models & Providers","dl":3019,"stars":0,"added":"2026-09-02","npm":1,"name":"dsh-model-health","owner":"oxlyn","short":"dsh-model-health","slug":"oxlyn/dsh-model-health","desc":"Model Health panel in Settings: lists every model configured in settings.yaml and batch-tests availability and latency for each.","cmd":"dsh plugin --profile web add dsh-model-health","href":"/p/oxlyn/dsh-model-health/"},{"cat":"model","tag":"Models & Providers","dl":2971,"stars":0,"added":"2026-10-13","npm":1,"name":"dsh-connect-agnes-token-plan","owner":"eghrhegpe","short":"dsh-connect-agnes-token-plan","slug":"eghrhegpe/dsh-connect-agnes-token-plan","desc":"One-tap connect Agnes language, image and video models into DSH (off by default), with image recognition and thinking level filled in automatically. After signing in to the Agnes console (re-login uses AGNES_PASSWORD), you can see the quota windows (5-hour requests, weekly requests, daily images, video), account-wide cumulative usage, and a usage pill beside the input box. AgnesCode desktop models can be connected too (Windows only), re-reading the desktop app login when the token expires, with rate-limit hits backing off on their own.","cmd":"dsh plugin --profile web add dsh-connect-agnes-token-plan","href":"/p/eghrhegpe/dsh-connect-agnes-token-plan/"},{"cat":"model","tag":"Models & Providers","dl":2955,"stars":17,"added":"2026-09-13","npm":1,"name":"dsh-oh-my-claude","owner":"lcestou","short":"dsh-oh-my-claude","slug":"lcestou/dsh-oh-my-claude","desc":"Runs your logged-in Claude Code CLI as a dsh model provider: live model list, session resume, approval relay, rewind, memory panel and remote SSH workspaces.","cmd":"dsh plugin --profile web add dsh-oh-my-claude","href":"/p/lcestou/dsh-oh-my-claude/"},{"cat":"model","tag":"Models & Providers","dl":2883,"stars":4,"added":"2026-08-23","npm":1,"name":"dsh-openrouter-providers","owner":"MoRanYue","short":"dsh-openrouter-providers","slug":"MoRanYue/dsh-openrouter-providers","desc":"Route OpenRouter requests through a configured provider list and quantization cap, injected as provider.only/order with allow_fallbacks, plus provider.quantizations.","cmd":"dsh plugin --profile web add dsh-openrouter-providers","href":"/p/MoRanYue/dsh-openrouter-providers/"},{"cat":"model","tag":"Models & Providers","dl":2859,"stars":1,"added":"2026-09-05","npm":1,"name":"dsh-reasoning-options","owner":"Scorp1o117","short":"dsh-reasoning-options","slug":"Scorp1o117/dsh-reasoning-options","desc":"Add missing reasoning-effort declarations to custom pi-ai models through DSH settings, enabling the native effort picker and handling models added later.","cmd":"dsh plugin --profile web add dsh-reasoning-options","href":"/p/Scorp1o117/dsh-reasoning-options/"},{"cat":"model","tag":"Models & Providers","dl":2783,"stars":1,"added":"2026-09-01","npm":1,"name":"dsh-agent-lang","owner":"KannaKuron","short":"dsh-agent-lang","slug":"KannaKuron/dsh-agent-lang","desc":"Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.","cmd":"dsh plugin --profile web add dsh-agent-lang","href":"/p/KannaKuron/dsh-agent-lang/"},{"cat":"model","tag":"Models & Providers","dl":2755,"stars":1,"added":"2026-10-18","npm":1,"name":"dsh-model-rotator","owner":"chimneyQ","short":"dsh-model-rotator","slug":"chimneyQ/dsh-model-rotator","desc":"Ranks the models a DeepSeek Harness install already discovered by measured connectivity and speed, and switches to the next candidate inside the same turn when the one in use fails without producing any output. Ships a settings page with a grouped model list, per-model and per-channel switches, and a quota-aware cooldown that rests an exhausted model until the next day.","cmd":"dsh plugin --profile web add dsh-model-rotator","href":"/p/chimneyQ/dsh-model-rotator/"},{"cat":"model","tag":"Models & Providers","dl":2740,"stars":56,"added":"2026-10-20","npm":1,"name":"dsh-qoder-connect","owner":"masknull","short":"dsh-qoder-connect","slug":"masknull/dsh-qoder-connect","desc":"Connects Qoder (China and Global) subscriptions to DSH through personal access tokens, keeping each variant on its own credentials and catalog, with saved-token switching, sidebar quota cards, per-model toggles, a context-window preference and a daily check-in.","cmd":"dsh plugin --profile web add dsh-qoder-connect","href":"/p/masknull/dsh-qoder-connect/"},{"cat":"model","tag":"Models & Providers","dl":2734,"stars":16,"added":"2026-10-17","npm":1,"name":"dsh-connect-qoder","owner":"dingminhua","short":"dsh-connect-qoder","slug":"dingminhua/dsh-connect-qoder","desc":"Connects Qoder (Lingma CN / international) models to DSH through their PATs, with a per-region multi-account pool, daily check-in, automatic failover, and read-only credit visibility.","cmd":"dsh plugin --profile web add @dmh2002/dsh-connect-qoder","href":"/p/dingminhua/dsh-connect-qoder/"},{"cat":"model","tag":"Models & Providers","dl":2638,"stars":21,"added":"2026-09-21","npm":1,"name":"dsh-provider-qoder","owner":"mo-n","short":"dsh-provider-qoder","slug":"mo-n/dsh-provider-qoder","desc":"Connects Qoder subscriptions to DeepSeek Harness, supporting Global and China regions, multimodal input, and tool calls.","cmd":"dsh plugin --profile web add dsh-provider-qoder","href":"/p/mo-n/dsh-provider-qoder/"},{"cat":"model","tag":"Models & Providers","dl":2526,"stars":8,"added":"2026-08-30","npm":1,"name":"dsh-router-codebuddy","owner":"CARVIN94","short":"dsh-router-codebuddy","slug":"CARVIN94/dsh-router-codebuddy","desc":"CodeBuddy supplier plugin for dsh-router. Handles one account at a time with polling OAuth login and token refresh, leaving account selection, cooldown and check-in to dsh-router core.","cmd":"dsh plugin --profile web add dsh-router-codebuddy","href":"/p/CARVIN94/dsh-router-codebuddy/"},{"cat":"model","tag":"Models & Providers","dl":2505,"stars":3,"added":"2026-10-16","npm":1,"name":"dsh-model-think-level","owner":"GaoHu1997","short":"dsh-model-think-level","slug":"GaoHu1997/dsh-model-think-level","desc":"Third-party model settings for DeepSeek Harness: pick a provider and a model in the composer menu, gate a model's thinking level with one switch on the official Models page card, and configure per-route request headers.","cmd":"dsh plugin --profile web add dsh-model-think-level","href":"/p/GaoHu1997/dsh-model-think-level/"},{"cat":"model","tag":"Models & Providers","dl":2481,"stars":2,"added":"2026-10-17","npm":1,"name":"dsh-model","owner":"AIcivilization","short":"dsh-model","slug":"AIcivilization/dsh-model","desc":"One authenticated OpenAI-compatible endpoint (built on CLIProxyAPI) for dsh and other tools: gathers WorkBuddy, OpenCode Zen, local Ollama / LM Studio and CLI subscriptions such as Codex and Kimi, signs in from the dsh page without installing their CLIs, and syncs the picked models into dsh grouped by source. The settings page has a switch per source with free / paid tags, plan usage, API keys with 24-hour stats, per-source model picking, and update / uninstall. Runs on macOS, Linux (including next to dsh-vps) and Windows.","cmd":"dsh plugin --profile web add dsh-model","href":"/p/AIcivilization/dsh-model/"},{"cat":"model","tag":"Models & Providers","dl":2467,"stars":12,"added":"2026-08-18","npm":1,"name":"dsh-llm-github-copilot","owner":"lujianjun19","short":"dsh-llm-github-copilot","slug":"lujianjun19/dsh-llm-github-copilot","desc":"GitHub Copilot LLM adapter: OAuth device-flow sign-in, live model discovery from the Copilot API, vision support for image-capable models (gpt-4.1, gpt-4o), and two wire protocols (Chat Completions and Responses API) with automatic endpoint routing per model.","cmd":"dsh plugin --profile web add @lujianjun19/dsh-llm-github-copilot","href":"/p/lujianjun19/dsh-llm-github-copilot/"},{"cat":"model","tag":"Models & Providers","dl":2405,"stars":8,"added":"2026-08-30","npm":1,"name":"dsh-reasoning-effort","owner":"Mu-scorpio","short":"dsh-reasoning-effort","slug":"Mu-scorpio/dsh-reasoning-effort","desc":"Configures provider and model reasoning-effort mappings for DeepSeek Harness, with a grouped model picker and composer slider.","cmd":"dsh plugin --profile web add dsh-reasoning-effort","href":"/p/Mu-scorpio/dsh-reasoning-effort/"},{"cat":"model","tag":"Models & Providers","dl":2379,"stars":2,"added":"2026-10-16","npm":1,"name":"modeltester","owner":"Yuer6327","short":"ModelTester","slug":"Yuer6327/ModelTester","desc":"Model attribution panel for the dsh web chat — local, zero-network structural fingerprinting (template token leaks, glitch canaries, tokenizer usage-vector matching) that scores which of 29 AI vendors a session's responses most resemble, with a per-claim evidence ledger and a 12-probe active battery.","cmd":"dsh plugin --profile web add dsh-modeltester","href":"/p/Yuer6327/ModelTester/"},{"cat":"model","tag":"Models & Providers","dl":2337,"stars":8,"added":"2026-09-05","npm":1,"name":"dsh-codebuddy-cli","owner":"fu827707013","short":"dsh-codebuddy-cli","slug":"fu827707013/dsh-codebuddy-cli","desc":"Reuses the CodeBuddy CLI sign-in to bring its models into DeepSeek Harness, with a settings card showing account, token expiry, and remaining credit.","cmd":"dsh plugin --profile web add dsh-codebuddy-cli","href":"/p/fu827707013/dsh-codebuddy-cli/"},{"cat":"model","tag":"Models & Providers","dl":2311,"stars":14,"added":"2026-09-15","npm":1,"name":"dsh-opencode-session","owner":"nobu121","short":"dsh-opencode-session","slug":"nobu121/dsh-opencode-session","desc":"Attaches a stable per-conversation x-opencode-session header to OpenCode / OpenCode Go provider requests, fixing 400 MissingSessionID errors and keeping session affinity and prompt-cache routing intact.","cmd":"dsh plugin --profile web add dsh-opencode-session","href":"/p/nobu121/dsh-opencode-session/"},{"cat":"model","tag":"Models & Providers","dl":2292,"stars":11,"added":"2026-08-19","npm":1,"name":"dsh-llm-retry-settings","owner":"zeng6125-rgb","short":"dsh-llm-retry-settings","slug":"zeng6125-rgb/dsh-llm-retry-settings","desc":"Settings card for the DSH LLM auto-retry engine: tune retry count, backoff and jitter live from Settings -> General, with configurable retryableCodes chips - defaults add INVALID_REQUEST so OpenAI-style HTTP 400 reasoning_text errors in thinking mode get retried automatically.","cmd":"dsh plugin --profile web add dsh-llm-retry-settings","href":"/p/zeng6125-rgb/dsh-llm-retry-settings/"},{"cat":"model","tag":"Models & Providers","dl":2286,"stars":1,"added":"2026-09-15","npm":1,"name":"dsh-model-channel-manager","owner":"ArcaneOrion","short":"dsh-model-channel-manager","slug":"ArcaneOrion/dsh-model-channel-manager","desc":"Model channel manager: several provider/model candidates share one virtual route (roundrobin/<group>) with failover, retry, timeout and cooldown; a settings tab edits providers and groups, runs per-model speed tests and real single-model request tests, and a seven-day health panel aggregates latency, failures and upstream token usage (input, output, cache and reasoning).","cmd":"dsh plugin --profile web add @arcaneorion/dsh-model-channel-manager","href":"/p/ArcaneOrion/dsh-model-channel-manager/"},{"cat":"model","tag":"Models & Providers","dl":2272,"stars":7,"added":"2026-09-05","npm":1,"name":"dsh-model-extension","owner":"lovezi0","short":"dsh-model-extension","slug":"lovezi0/dsh-model-extension","desc":"Models+ settings page for the DSH web UI: per-model reasoning-effort tables, input modalities and compat flags saved through the official settings pipeline, with models.dev metadata prefill and API key management.","cmd":"dsh plugin --profile web add dsh-model-extension","href":"/p/lovezi0/dsh-model-extension/"},{"cat":"model","tag":"Models & Providers","dl":2233,"stars":4,"added":"2026-09-25","npm":1,"name":"dsh-mimo-connect","owner":"anze225-max","short":"dsh-mimo-connect","slug":"anze225-max/dsh-mimo-connect","desc":"Brings the models included in the Xiaomi MiMo desktop app (free during beta) into DeepSeek Harness, with zero configuration in the DSH conversation window.","cmd":"dsh plugin --profile web add dsh-mimo-connect","href":"/p/anze225-max/dsh-mimo-connect/"},{"cat":"model","tag":"Models & Providers","dl":2223,"stars":267,"added":"2026-09-04","npm":1,"name":"dsh-xdpool","owner":"XDTrees","short":"dsh-xdpool","slug":"XDTrees/dsh-xdpool","desc":"Merge every locally signed-in WorkBuddy account into DeepSeek Harness as one auto-failing-over model pool: multi-account rotation, 429 cooldowns, live credits, a model catalog with per-model credit multipliers and free/night-discount tags, QR-code login for 13 vendors, and aggregate free-tier channels. Accounts persist across restarts.","cmd":"dsh plugin --profile web add dsh-xdpool","href":"/p/XDTrees/dsh-xdpool/"},{"cat":"model","tag":"Models & Providers","dl":2190,"stars":7,"added":"2026-08-30","npm":1,"name":"dsh-router-traework","owner":"CARVIN94","short":"dsh-router-traework","slug":"CARVIN94/dsh-router-traework","desc":"TRAE SOLO supplier plugin for dsh-router, ported from traework2api. Provides the traework supplier, a free SOLO chat channel, and reports single-account status to dsh-router core.","cmd":"dsh plugin --profile web add dsh-router-traework","href":"/p/CARVIN94/dsh-router-traework/"},{"cat":"model","tag":"Models & Providers","dl":2177,"stars":12,"added":"2026-09-05","npm":1,"name":"owndsh#owndsh-plugin","owner":"boe1900","short":"owndsh#owndsh-plugin","slug":"boe1900/owndsh--plugin-packages-bundle","desc":"Early-stage plugin connecting DeepSeek Harness to a separately deployed, self-hosted OwnDsh server for team identity, model access control, quotas, and usage auditing.","cmd":"dsh plugin --profile web add owndsh-plugin","href":"/p/boe1900/owndsh--plugin-packages-bundle/"},{"cat":"model","tag":"Models & Providers","dl":2139,"stars":30,"added":"2026-09-05","npm":1,"name":"dsh-model-context-catalog","owner":"HOWILLMAKEIT","short":"dsh-model-context-catalog","slug":"HOWILLMAKEIT/dsh-model-context-catalog","desc":"Match context windows for configured DSH models in one click, show capacity sources, and support selective bulk configuration, manual editing, and continuous synchronization.","cmd":"dsh plugin --profile web add dsh-model-context-catalog","href":"/p/HOWILLMAKEIT/dsh-model-context-catalog/"},{"cat":"model","tag":"Models & Providers","dl":2108,"stars":20,"added":"2026-08-14","npm":1,"name":"dsh-codex-auth","owner":"suntianc","short":"dsh-codex-auth","slug":"suntianc/dsh-codex-auth","desc":"Reuses the Codex CLI ChatGPT login as an `openai-codex` LLM route and adds GPT Auth controls to DSH Web settings.","cmd":"dsh plugin --profile web add dsh-codex-auth","href":"/p/suntianc/dsh-codex-auth/"},{"cat":"model","tag":"Models & Providers","dl":2007,"stars":0,"added":"2026-09-11","npm":1,"name":"dsh-model-probe","owner":"xiaomao49","short":"dsh-model-probe","slug":"xiaomao49/dsh-model-probe","desc":"Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.","cmd":"dsh plugin --profile web add dsh-model-probe","href":"/p/xiaomao49/dsh-model-probe/"},{"cat":"model","tag":"Models & Providers","dl":1881,"stars":3,"added":"2026-09-07","npm":1,"name":"dsh-model-prompt-injector","owner":"MoonlitDropOfBlood","short":"dsh-model-prompt-injector","slug":"MoonlitDropOfBlood/dsh-model-prompt-injector","desc":"Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.","cmd":"dsh plugin --profile web add @duke-dsh-plugins/dsh-model-prompt-injector","href":"/p/MoonlitDropOfBlood/dsh-model-prompt-injector/"},{"cat":"model","tag":"Models & Providers","dl":1849,"stars":26,"added":"2026-08-18","npm":1,"name":"dsh-coding-subscription-oauth","owner":"lninghaha","short":"dsh-coding-subscription-oauth","slug":"lninghaha/dsh-coding-subscription-oauth","desc":"Coding-subscription OAuth for SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code and Claude Code, plus an opt-in loopback OpenAI/Anthropic gateway: local login without pasting tokens, AUTH refresh-and-retry, grok-4.6 xhigh, and API-key route coexistence.","cmd":"dsh plugin --profile web add dsh-coding-subscription-oauth","href":"/p/lninghaha/dsh-coding-subscription-oauth/"},{"cat":"model","tag":"Models & Providers","dl":1833,"stars":22,"added":"2026-09-07","npm":1,"name":"dsh-chatgpt-web","owner":"WLV-ZEDD","short":"dsh-chatgpt-web","slug":"WLV-ZEDD/dsh-chatgpt-web","desc":"Free conversational ChatGPT Web (GPT 5.6 Luna) model provider for DeepSeek Harness with streaming Markdown.","cmd":"dsh plugin --profile web add @wlv-zedd/dsh-chatgpt-web","href":"/p/WLV-ZEDD/dsh-chatgpt-web/"},{"cat":"model","tag":"Models & Providers","dl":1796,"stars":18,"added":"2026-09-05","npm":1,"name":"dsh-opencode-free-models#dsh-opencode-free-models","owner":"yu-wenchao","short":"dsh-opencode-free-models#dsh-opencode-free-models","slug":"yu-wenchao/dsh-opencode-free-models--plugin-dsh-opencode-free-models","desc":"Free model provider plugin for DSH with 20+ models including Gemini, MiMo, GLM, etc.","cmd":"dsh plugin --profile web add dsh-opencode-free-models","href":"/p/yu-wenchao/dsh-opencode-free-models--plugin-dsh-opencode-free-models/"},{"cat":"model","tag":"Models & Providers","dl":1783,"stars":1,"added":"2026-09-15","npm":1,"name":"dsh-plugin-subagent-roles","owner":"troytse","short":"dsh-plugin-subagent-roles","slug":"troytse/dsh-plugin-subagent-roles","desc":"File-defined subagent roles for DeepSeek Harness: roles live in project and global .dsh/roles files, a delegating agent sees one catalog line per role, and each role's tool policy decides which tools its child can see.","cmd":"dsh plugin --profile web add dsh-plugin-subagent-roles","href":"/p/troytse/dsh-plugin-subagent-roles/"},{"cat":"model","tag":"Models & Providers","dl":1760,"stars":2,"added":"2026-08-19","npm":1,"name":"dsh-delegate-router","owner":"penguin-oo","short":"dsh-delegate-router","slug":"penguin-oo/dsh-delegate-router","desc":"Automatic Flash/Pro routing for DeepSeek Harness subagent calls: light tasks run on a cheap model (e.g. V4 Flash), heavy tasks stay on the strong model — with per-call overrides and /delegate session modes.","cmd":"dsh plugin --profile web add dsh-delegate-router","href":"/p/penguin-oo/dsh-delegate-router/"},{"cat":"model","tag":"Models & Providers","dl":1740,"stars":3,"added":"2026-09-15","npm":1,"name":"dsh-model-fold","owner":"loyalchiiina","short":"dsh-model-fold","slug":"loyalchiiina/dsh-model-fold","desc":"Groups the DSH model picker by provider: the menu lists sources with their model counts, and hovering a source slides that provider's models out in a side panel (default); in panel mode a click opens the same panel, and double-clicking a source title cycles hover -> panel -> inline (expand below the title). The active model stays visible at a glance. Pure DOM enhancement with zero intrusion - the panel is plugin-owned DOM mounted on body and selection happens by programmatically clicking the real menu buttons, so no React-managed node is moved or removed, keeping the host rendering intact and coexisting with other UI plugins. Styling follows the host by reusing the official --dsw-* theme tokens, with an enforced opaque background, sufficient contrast, and one shared set of sizing and colour tokens for both menu levels. No network access and no telemetry. Built for DSH kernel 2.0.15-next.","cmd":"dsh plugin --profile web add dsh-model-fold","href":"/p/loyalchiiina/dsh-model-fold/"},{"cat":"model","tag":"Models & Providers","dl":1685,"stars":1,"added":"2026-09-13","npm":1,"name":"dsh-peakrate","owner":"log-li","short":"dsh-peakrate","slug":"log-li/dsh-peakrate","desc":"Peak / off-peak rate badges for the model selector (every row) and the composer tool row, judged per provider by its own time zone and schedule; the live catalog is served from the host over a fenced route.","cmd":"dsh plugin --profile web add dsh-peakrate","href":"/p/log-li/dsh-peakrate/"},{"cat":"model","tag":"Models & Providers","dl":1675,"stars":21,"added":"2026-10-14","npm":1,"name":"dsh-workbuddy-bridge","owner":"dsh-plugin-lab","short":"dsh-workbuddy-bridge","slug":"dsh-plugin-lab/dsh-workbuddy-bridge","desc":"Brings WorkBuddy desktop-app models into DeepSeek Harness: the China and international builds each appear as their own group in the model picker, with the reasoning tiers the upstream declares, per-reply credit cost and remaining balance, per-account model visibility, and image input where supported.","cmd":"dsh plugin --profile web add dsh-workbuddy-bridge","href":"/p/dsh-plugin-lab/dsh-workbuddy-bridge/"},{"cat":"model","tag":"Models & Providers","dl":1675,"stars":6,"added":"2026-08-29","npm":1,"name":"dsh-oauth-adapter","owner":"edge-sky","short":"dsh-oauth-adapter","slug":"edge-sky/dsh-oauth-adapter","desc":"Provides an OAuth account page for DSH Web, currently supporting OpenAI Codex, GitHub Copilot, Anthropic, Kimi For Coding, OpenRouter, and xAI.","cmd":"dsh plugin --profile web add @edge-sky/dsh-oauth-adapter","href":"/p/edge-sky/dsh-oauth-adapter/"},{"cat":"model","tag":"Models & Providers","dl":1645,"stars":23,"added":"2026-08-22","npm":1,"name":"dsh-antigravity-auth","owner":"suntianc","short":"dsh-antigravity-auth","slug":"suntianc/dsh-antigravity-auth","desc":"Adds an unofficial Antigravity OAuth-backed LLM route, web search, image generation and editing, video understanding, quota status, and DSH Web settings controls.","cmd":"dsh plugin --profile web add dsh-antigravity-auth","href":"/p/suntianc/dsh-antigravity-auth/"},{"cat":"model","tag":"Models & Providers","dl":1643,"stars":6,"added":"2026-08-30","npm":1,"name":"dsh-plugin-model-capability","owner":"yuioi666","short":"dsh-plugin-model-capability","slug":"yuioi666/dsh-plugin-model-capability","desc":"Model Capability Manager for DSH Web: thinking levels, context window, output caps, input modalities, gateway compat presets, EN/中文 UI.","cmd":"dsh plugin --profile web add dsh-plugin-model-capability","href":"/p/yuioi666/dsh-plugin-model-capability/"},{"cat":"model","tag":"Models & Providers","dl":1639,"stars":26,"added":"2026-08-20","npm":1,"name":"dsh-antigravity","owner":"LiZhenNet","short":"dsh-antigravity","slug":"LiZhenNet/dsh-antigravity","desc":"Google Antigravity / Cloud Code Assist model provider with quota management and model selector.","cmd":"dsh plugin --profile web add dsh-antigravity","href":"/p/LiZhenNet/dsh-antigravity/"},{"cat":"model","tag":"Models & Providers","dl":1611,"stars":8,"added":"2026-08-22","npm":1,"name":"dsh-model-pro","owner":"wqy8593521","short":"dsh-model-pro","slug":"wqy8593521/dsh-model-pro","desc":"Lifecycle management UI for the llm-pi-ai model provider: create, edit, delete, enable and disable providers with custom headers and AES-GCM-encrypted API keys; uninstall-safe restore of parked providers, remote model discovery with batch write, smart routing with five strategies, union/intersection composites, per-model connectivity tests, and request observability.","cmd":"dsh plugin --profile web add dsh-model-pro","href":"/p/wqy8593521/dsh-model-pro/"},{"cat":"model","tag":"Models & Providers","dl":1578,"stars":4,"added":"2026-10-16","npm":1,"name":"dsh-magpie-connect","owner":"bitxeno","short":"dsh-magpie-connect","slug":"bitxeno/dsh-magpie-connect","desc":"Magpie gateway provider for DSH: syncs gateway models into the picker with visibility control, image input and thinking levels.","cmd":"dsh plugin --profile web add dsh-magpie-connect","href":"/p/bitxeno/dsh-magpie-connect/"},{"cat":"model","tag":"Models & Providers","dl":1570,"stars":148,"added":"2026-09-02","npm":1,"name":"ark-cli#ark-plan-api","owner":"volcengine","short":"ark-cli#ark-plan-api","slug":"volcengine/ark-cli--dsh-plugins-ark-plan-api","desc":"Registers Ark Agent Plan, Coding Plan and postpaid model routes in the native DSH model picker.","cmd":"dsh plugin --profile web add @volcengine/ark-plan-api","href":"/p/volcengine/ark-cli--dsh-plugins-ark-plan-api/"},{"cat":"model","tag":"Models & Providers","dl":1511,"stars":0,"added":"2026-09-20","npm":1,"name":"dsh-lantern","owner":"Saretheya","short":"dsh-lantern","slug":"Saretheya/dsh-lantern","desc":"Expose every model already configured in your local DeepSeek Harness to the LAN over OpenAI- and Anthropic-compatible endpoints, with API keys, per-key rate limits, a circuit breaker, model filters and usage reports.","cmd":"dsh plugin --profile web add dsh-lantern","href":"/p/Saretheya/dsh-lantern/"},{"cat":"model","tag":"Models & Providers","dl":1497,"stars":7,"added":"2026-08-19","npm":1,"name":"dsh-llm-proxy","owner":"superfish058","short":"dsh-llm-proxy","slug":"superfish058/dsh-llm-proxy","desc":"Per-model proxy routing for LLM requests: selected models go through a proxy (Clash etc.) while the rest stay direct, with automatic retry on transport errors, 429 and 5xx, configured live from the settings page.","cmd":"dsh plugin --profile web add @superfish058/dsh-llm-proxy","href":"/p/superfish058/dsh-llm-proxy/"},{"cat":"model","tag":"Models & Providers","dl":1490,"stars":10,"added":"2026-10-14","npm":1,"name":"dsh-workbuddy-connect-functy","owner":"functy23","short":"dsh-workbuddy-connect-functy","slug":"functy23/dsh-workbuddy-connect-functy","desc":"Functy fork of corrinehu/dsh-workbuddy-connect. Brings WorkBuddy desktop-app models into DeepSeek Harness with a dashboard UI, multi-account rotation, and sidebar credit.","cmd":"dsh plugin --profile web add dsh-workbuddy-connect-functy","href":"/p/functy23/dsh-workbuddy-connect-functy/"},{"cat":"model","tag":"Models & Providers","dl":1472,"stars":1,"added":"2026-08-30","npm":1,"name":"dsh-llm-openai-completions","owner":"drscrewdriver","short":"dsh-llm-openai-completions","slug":"drscrewdriver/dsh-llm-openai-completions","desc":"OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:\"system\", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).","cmd":"dsh plugin --profile web add dsh-llm-openai-completions","href":"/p/drscrewdriver/dsh-llm-openai-completions/"},{"cat":"model","tag":"Models & Providers","dl":1465,"stars":3,"added":"2026-09-18","npm":1,"name":"dsh-plugin#dsh-llm-pi-gateway","owner":"mzzsfy","short":"dsh-plugin#dsh-llm-pi-gateway","slug":"mzzsfy/dsh-plugin--packages-dsh-llm-pi-gateway","desc":"Session-affinity routing for LLM gateways: injects the session ID into every request sent to NewApi-style gateways so the gateway can pin requests per session and raise prompt-cache hits; takes over the official pi-ai routing on install and restores it on uninstall.","cmd":"dsh plugin --profile web add @mzzsfy/dsh-llm-pi-gateway","href":"/p/mzzsfy/dsh-plugin--packages-dsh-llm-pi-gateway/"},{"cat":"model","tag":"Models & Providers","dl":1465,"stars":0,"added":"2026-09-20","npm":1,"name":"dsh-router-loomy","owner":"2404723600","short":"dsh-router-loomy","slug":"2404723600/dsh-router-loomy","desc":"Registers the Xunfei Loomy cloud channel as an OpenAI-compatible supplier in dsh-router, adding model listing and streaming chat completions.","cmd":"dsh plugin --profile web add dsh-router-loomy","href":"/p/2404723600/dsh-router-loomy/"},{"cat":"model","tag":"Models & Providers","dl":1437,"stars":2,"added":"2026-09-10","npm":1,"name":"dsh-model-pricing","owner":"vitas","short":"dsh-model-pricing","slug":"vitas/dsh-model-pricing","desc":"Model pricing for the DSH settings page: ~7,250 models / 213 providers with the harness catalog overlaid, honest lowest-listed comparison, session costs priced by the actual route, cache-leak attribution, and a verified promotion feed.","cmd":"dsh plugin --profile web add dsh-model-pricing","href":"/p/vitas/dsh-model-pricing/"},{"cat":"model","tag":"Models & Providers","dl":1425,"stars":7,"added":"2026-08-30","npm":1,"name":"kimi-tide#dsh-kimi-tide","owner":"tafcear","short":"kimi-tide#dsh-kimi-tide","slug":"tafcear/kimi-tide--packages-dsh-kimi-tide","desc":"Per-step model router: named presets with ordered image/keyword-group rules route each agent step across every mounted provider and model, adding collaboration flows for image transcription, an image guard, a multi-plan quota panel, and per-step decision observability.","cmd":"dsh plugin --profile web add dsh-kimi-tide","href":"/p/tafcear/kimi-tide--packages-dsh-kimi-tide/"},{"cat":"model","tag":"Models & Providers","dl":1418,"stars":3,"added":"2026-10-16","npm":1,"name":"dsh-llm-opencode-go-live","owner":"SkylerFee","short":"dsh-llm-opencode-go-live","slug":"SkylerFee/dsh-llm-opencode-go-live","desc":"An OpenCode Go model source for DSH: it reads the opencode-go catalog from Models.dev and serves it on a separate opencode-go-live route, leaving the built-in opencode-go route in place. The catalog snapshot is cached under the DSH home and a failed refresh keeps the last successful one; its own Models settings card edits the route key and can render OpenCode Go subscription usage.","cmd":"dsh plugin --profile web add @skylerfee/dsh-llm-opencode-go-live","href":"/p/SkylerFee/dsh-llm-opencode-go-live/"},{"cat":"model","tag":"Models & Providers","dl":1416,"stars":1,"added":"2026-08-19","npm":1,"name":"dsh-plugin-thinking-api","owner":"qjf44","short":"dsh-plugin-thinking-api","slug":"qjf44/dsh-plugin-thinking-api","desc":"One-click OpenAI-compatible API (CodeBuddy/vLLM/proxies) with thinking mode, avoiding developer-role content_filter rejection.","cmd":"dsh plugin --profile web add dsh-plugin-thinking-api","href":"/p/qjf44/dsh-plugin-thinking-api/"},{"cat":"model","tag":"Models & Providers","dl":1396,"stars":2,"added":"2026-10-17","npm":1,"name":"dsh-connect-modelscope-token-plan","owner":"eghrhegpe","short":"dsh-connect-modelscope-token-plan","slug":"eghrhegpe/dsh-connect-modelscope-token-plan","desc":"One-tap connect ModelScope language and image-generation models into DSH (off by default), with image recognition and context window filled in automatically. You can also see the free Magicube balance, jump to a model's info page, and record local call counts, trends and rate-limit events, with a usage pill beside the input box showing the balance and today's local count. All of it needs only an API key, with no account sign-in.","cmd":"dsh plugin --profile web add dsh-connect-modelscope-token-plan","href":"/p/eghrhegpe/dsh-connect-modelscope-token-plan/"},{"cat":"model","tag":"Models & Providers","dl":1395,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-model-router","owner":"ebluffy","short":"dsh-model-router","slug":"ebluffy/dsh-model-router","desc":"English-only fork of dsh-model-router. Routes each agent step across a configurable model pool and adjusts reasoning effort based on task complexity, tool failures, and cost.","cmd":"dsh plugin --profile web add dsh-model-router-en","href":"/p/ebluffy/dsh-model-router/"},{"cat":"model","tag":"Models & Providers","dl":1381,"stars":0,"added":"2026-09-24","npm":1,"name":"dsh-xai-oauth","owner":"tonylee2022","short":"dsh-xai-oauth","slug":"tonylee2022/dsh-xai-oauth","desc":"Sign in to an xAI Grok subscription with device-code OAuth, refresh the access token, and use it as the xai route credential without an API key.","cmd":"dsh plugin --profile web add dsh-xai-oauth","href":"/p/tonylee2022/dsh-xai-oauth/"},{"cat":"model","tag":"Models & Providers","dl":1358,"stars":7,"added":"2026-08-23","npm":1,"name":"dsh-codex-harness","owner":"shuind","short":"dsh-codex-harness","slug":"shuind/dsh-codex-harness","desc":"Compact Codex coding mode for DSH: light prompt guardrails against GPT over-explaining, with an editable prompt and native Codex-style tools.","cmd":"dsh plugin --profile web add @shuind/dsh-codex-harness","href":"/p/shuind/dsh-codex-harness/"},{"cat":"model","tag":"Models & Providers","dl":1343,"stars":3,"added":"2026-08-27","npm":1,"name":"dsh-models-radar","owner":"hi-fangj","short":"dsh-models-radar","slug":"hi-fangj/dsh-models-radar","desc":"Displays CodexRadar model capability benchmarks in a Settings page and shows the selected session model's DeepSWE score beside the composer.","cmd":"dsh plugin --profile web add dsh-models-radar","href":"/p/hi-fangj/dsh-models-radar/"},{"cat":"model","tag":"Models & Providers","dl":1337,"stars":4,"added":"2026-10-17","npm":1,"name":"dsh-codearts","owner":"elegant01","short":"dsh-codearts","slug":"elegant01/dsh-codearts","desc":"Connects Huawei Cloud CodeArts to DeepSeek Harness: built-in Huawei Cloud OAuth2 sign-in (PKCE + DPoP) or a pasted token, after which CodeArts models are available in the DSH conversation window, with local per-account request and token usage.","cmd":"dsh plugin --profile web add dsh-codearts","href":"/p/elegant01/dsh-codearts/"},{"cat":"model","tag":"Models & Providers","dl":1308,"stars":5,"added":"2026-08-23","npm":1,"name":"dsh-plugin-rollout-scout","owner":"SpookySandwich","short":"dsh-plugin-rollout-scout","slug":"SpookySandwich/dsh-plugin-rollout-scout","desc":"Detects which conversation model an account is being served: launches concurrent throwaway probe conversations, scores each streaming chain-of-thought by how its paragraphs open, and cancels probes that read as the older model within seconds. Includes an offline self-check that replays 13 hand-labelled chains-of-thought through the same classifier.","cmd":"dsh plugin --profile web add dsh-plugin-rollout-scout","href":"/p/SpookySandwich/dsh-plugin-rollout-scout/"},{"cat":"model","tag":"Models & Providers","dl":1294,"stars":3,"added":"2026-09-20","npm":1,"name":"dsh-set-model","owner":"john-walks-slow","short":"dsh-set-model","slug":"john-walks-slow/dsh-set-model","desc":"Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.","cmd":"dsh plugin --profile web add dsh-set-model","href":"/p/john-walks-slow/dsh-set-model/"},{"cat":"model","tag":"Models & Providers","dl":1254,"stars":1,"added":"2026-08-31","npm":1,"name":"daruma#dsh-daruma","owner":"SISCHOI","short":"daruma#dsh-daruma","slug":"SISCHOI/daruma--packages-dsh-daruma","desc":"Keeps long DSH sessions alive when a model channel starts failing: daruma takes over after the in-box retry gives up, trips a self-healing circuit breaker on repeated 429/5xx or a terminal error, and moves the next request to another channel in your chain. Works on DSH 0.1.x and 0.2.x hosts, including 0.2.1-rc.2 with verified failover and backup-management RPC. The backup can be picked in Settings or from a panel beside the composer — both stay in sync — with a durable JSONL audit log for every switch. Channel switches are recorded in that audit log instead of as in-conversation notice rows, because a plugin session event of a type the host does not know makes it refuse to load the whole session.","cmd":"dsh plugin --profile web add dsh-daruma","href":"/p/SISCHOI/daruma--packages-dsh-daruma/"},{"cat":"model","tag":"Models & Providers","dl":1250,"stars":5,"added":"2026-10-17","npm":1,"name":"dsh-sensenova-pool","owner":"Phoeky","short":"dsh-sensenova-pool","slug":"Phoeky/dsh-sensenova-pool","desc":"Brings SenseNova (日日新) models into dsh with a per-key rotation pool: paste any number of API keys and requests rotate across them, a 429 rate-limit immediately retries on the next key with per-key exponential-backoff cooldown, local RPM pre-throttling avoids the limit instead of reacting to it, and an exhausted pool answers 503 with Retry-After so a 429 never reaches the caller. Ships a built-in model catalogue that works offline and refreshes from /v1/models, plus a settings card with masked keys, per-key probing and removal.","cmd":"dsh plugin --profile web add dsh-sensenova-pool","href":"/p/Phoeky/dsh-sensenova-pool/"},{"cat":"model","tag":"Models & Providers","dl":1234,"stars":4,"added":"2026-08-28","npm":1,"name":"dsh-llm-qwen-local","owner":"starefinger","short":"dsh-llm-qwen-local","slug":"starefinger/dsh-llm-qwen-local","desc":"LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint, with per-model multimodal switch, fully configurable reasoning efforts, and a web settings page for editing the deployment from the frontend.","cmd":"dsh plugin --profile web add dsh-llm-qwen-local","href":"/p/starefinger/dsh-llm-qwen-local/"},{"cat":"model","tag":"Models & Providers","dl":1205,"stars":1,"added":"2026-09-06","npm":1,"name":"dsh-advisor-group","owner":"xingzhen199186","short":"dsh-advisor-group","slug":"xingzhen199186/dsh-advisor-group","desc":"Consult multiple expert advisor models in a retro CRT chat-group card: one ask_advisors call runs an auto-deepen pipeline (driver deep-question, advisor relay, synthesis conclusion) with SSE streaming, 26 provider presets, a configurable daily quota, stop/resume, and optional advisor tool calling.","cmd":"dsh plugin --profile web add dsh-advisor-group","href":"/p/xingzhen199186/dsh-advisor-group/"},{"cat":"model","tag":"Models & Providers","dl":1185,"stars":0,"added":"2026-09-03","npm":1,"name":"dsh-codex-harness","owner":"bainianlaoyao","short":"dsh-codex-harness","slug":"bainianlaoyao/dsh-codex-harness","desc":"Codex-shaped coding tools and agent presets for GPT models on DeepSeek Harness: exec_command, write_stdin, apply_patch and view_image, plus OpenAI Chat Completions and Responses API routes, bridged to DSH-native plan, ask, approval and compaction. Long-running commands become DSH background jobs with bounded head/tail output readable through job_output, and each subagent type can be pinned to its own preset, provider, model and reasoning effort.","cmd":"dsh plugin --profile web add dsh-codex-mode","href":"/p/bainianlaoyao/dsh-codex-harness/"},{"cat":"model","tag":"Models & Providers","dl":1161,"stars":69,"added":"2026-10-13","npm":1,"name":"dsh-model-fusion","owner":"aa2246740","short":"dsh-model-fusion","slug":"aa2246740/dsh-model-fusion","desc":"Adds a model route where a Lead plans and reviews while a Sidekick performs code changes.","cmd":"dsh plugin --profile web add dsh-model-fusion","href":"/p/aa2246740/dsh-model-fusion/"},{"cat":"model","tag":"Models & Providers","dl":1158,"stars":2,"added":"2026-08-27","npm":1,"name":"dsh-modellix","owner":"Modellix","short":"dsh-modellix","slug":"Modellix/dsh-modellix","desc":"Modellix integration for DSH: schema-driven image, video and audio generation in a split Design workspace, a live LLM model catalog, and native web search and fetch providers through one API key.","cmd":"dsh plugin --profile web add dsh-modellix","href":"/p/Modellix/dsh-modellix/"},{"cat":"model","tag":"Models & Providers","dl":1109,"stars":0,"added":"2026-09-24","npm":1,"name":"dsh-openrouter-live","owner":"Boomerangz","short":"dsh-openrouter-live","slug":"Boomerangz/dsh-openrouter-live","desc":"OpenRouter provider that reads the live /models list, so new models appear without a harness release: models sorted by name with input/output prices, per-model reasoning levels, image input, reasoning_details replay, Anthropic prompt caching, and actual spend per session including subagents from OpenRouter usage.cost, shown under the Web UI composer and by /cost.","cmd":"dsh plugin --profile web add dsh-openrouter-live","href":"/p/Boomerangz/dsh-openrouter-live/"},{"cat":"model","tag":"Models & Providers","dl":1097,"stars":3,"added":"2026-08-15","npm":1,"name":"dsh-sub2api","owner":"GodD6366","short":"dsh-sub2api","slug":"GodD6366/dsh-sub2api","desc":"Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vision/image tools.","cmd":"dsh plugin --profile web add @godd6366/dsh-sub2api","href":"/p/GodD6366/dsh-sub2api/"},{"cat":"model","tag":"Models & Providers","dl":1097,"stars":2,"added":"2026-09-05","npm":1,"name":"dsh-model-memory","owner":"Mutx163","short":"dsh-model-memory","slug":"Mutx163/dsh-model-memory","desc":"Reasoning-effort tier manager for custom API models plus cross-session preference memory: inline low/medium/high/max toggles inside Settings → Models, with atomic settings writes.","cmd":"dsh plugin --profile web add dsh-model-memory","href":"/p/Mutx163/dsh-model-memory/"},{"cat":"model","tag":"Models & Providers","dl":1077,"stars":10,"added":"2026-09-05","npm":1,"name":"dsh-agy-safe","owner":"Jonah-Wu23","short":"dsh-agy-safe","slug":"Jonah-Wu23/dsh-agy-safe","desc":"Compliantly use your own Antigravity quota in dsh: bridges your local logged-in official Antigravity CLI (agy) session as the chat and subagent model provider.","cmd":"dsh plugin --profile web add dsh-agy-safe","href":"/p/Jonah-Wu23/dsh-agy-safe/"},{"cat":"model","tag":"Models & Providers","dl":1060,"stars":1,"added":"2026-08-23","npm":1,"name":"dsh-codex-switch","owner":"ZChenW","short":"dsh-codex-switch","slug":"ZChenW/dsh-codex-switch","desc":"Connects ChatGPT accounts through OAuth, switches among them manually or automatically, and adds Codex models with usage limits to DeepSeek Harness.","cmd":"dsh plugin --profile web add dsh-codex-switch","href":"/p/ZChenW/dsh-codex-switch/"},{"cat":"model","tag":"Models & Providers","dl":1059,"stars":2,"added":"2026-08-27","npm":1,"name":"dsh-grok-provider","owner":"yoshino-xiao7","short":"dsh-grok-provider","slug":"yoshino-xiao7/dsh-grok-provider","desc":"Grok Build provider using the official CLI browser login, with dynamic account-visible models, streaming reasoning and tools, plus quota and model-capability settings.","cmd":"dsh plugin --profile web add dsh-grok-provider","href":"/p/yoshino-xiao7/dsh-grok-provider/"},{"cat":"model","tag":"Models & Providers","dl":1042,"stars":1,"added":"2026-10-16","npm":1,"name":"dsh-proxy-routes","owner":"liqiaohuia","short":"dsh-proxy-routes","slug":"liqiaohuia/dsh-proxy-routes","desc":"Per-provider (account) proxy routing for DSH. SOCKS5/HTTP proxy pool with account-level routing based on API keys. Supports forced direct connections and hot-swapping built-in web tools proxies. Managed via a graphical settings page in DSH.","cmd":"dsh plugin --profile web add dsh-proxy-routes","href":"/p/liqiaohuia/dsh-proxy-routes/"},{"cat":"model","tag":"Models & Providers","dl":1036,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-spark-scope","owner":"juliankang4","short":"dsh-spark-scope","slug":"juliankang4/dsh-spark-scope","desc":"Shows a Spark Scope card at the bottom of the dsh sidebar: model server decode and prefill rates with sparklines, running and queued requests, KV cache, TTFT and TPOT p95, and GPU temperature, power, load and memory for each DGX Spark node. Read-only; needs a running Spark Scope server. Works in dsh web and the desktop app.","cmd":"dsh plugin --profile web add dsh-spark-scope","href":"/p/juliankang4/dsh-spark-scope/"},{"cat":"model","tag":"Models & Providers","dl":1034,"stars":6,"added":"2026-09-19","npm":1,"name":"dsh-opencode-go-model-list","owner":"xiaobbl","short":"dsh-opencode-go-model-list","slug":"xiaobbl/dsh-opencode-go-model-list","desc":"Serves the live opencode Go model catalog from the harness's built-in opencode-go provider route.","cmd":"dsh plugin --profile web add dsh-opencode-go-model-list","href":"/p/xiaobbl/dsh-opencode-go-model-list/"},{"cat":"model","tag":"Models & Providers","dl":1032,"stars":0,"added":"2026-08-27","npm":1,"name":"dsh-openrouter-provider-advisor","owner":"xuan666-lab","short":"dsh-openrouter-provider-advisor","slug":"xuan666-lab/dsh-openrouter-provider-advisor","desc":"Ranks OpenRouter providers for the current DSH model by quantization, speed, cache-heavy price, context, and uptime, with one-click switching to help reduce token costs.","cmd":"dsh plugin --profile web add dsh-openrouter-provider-advisor","href":"/p/xuan666-lab/dsh-openrouter-provider-advisor/"},{"cat":"model","tag":"Models & Providers","dl":1003,"stars":1,"added":"2026-08-25","npm":1,"name":"dsh-model-gate","owner":"OPaimon","short":"dsh-model-gate","slug":"OPaimon/dsh-model-gate","desc":"Single-model disable gate: hides denied models from DSH catalogs, blocks direct dispatch with an in-protocol error chunk, and exposes a settings UI for the denylist.","cmd":"dsh plugin --profile web add dsh-model-gate","href":"/p/OPaimon/dsh-model-gate/"},{"cat":"model","tag":"Models & Providers","dl":1002,"stars":0,"added":"2026-09-15","npm":1,"name":"dsh-reasoning-tiers","owner":"1069137617","short":"dsh-reasoning-tiers","slug":"1069137617/dsh-reasoning-tiers","desc":"Declares per-model reasoning-effort ladders for third-party providers in the llm-pi-ai settings section, so DSH's stock thinking-intensity selector works on models the pi-ai catalog does not describe.","cmd":"dsh plugin --profile web add dsh-reasoning-tiers","href":"/p/1069137617/dsh-reasoning-tiers/"},{"cat":"model","tag":"Models & Providers","dl":994,"stars":1,"added":"2026-10-17","npm":1,"name":"dsh-model-tidy","owner":"star-Cosmo","short":"dsh-model-tidy","slug":"star-Cosmo/dsh-model-tidy","desc":"Tidy the model list of DeepSeek Harness: hide any model from the selector, rename models and channels while keeping the provider billing rate, and arrange both with arrows. Search, per-provider batch toggles, back to top, one-click restore. Display only — no provider configuration is rewritten.","cmd":"dsh plugin --profile web add dsh-model-tidy","href":"/p/star-Cosmo/dsh-model-tidy/"},{"cat":"model","tag":"Models & Providers","dl":993,"stars":5,"added":"2026-08-19","npm":1,"name":"dsh-role-router","owner":"SnowAmberX","short":"dsh-role-router","slug":"SnowAmberX/dsh-role-router","desc":"Routes agent requests to configurable default, planner, and subagent models, automatically using the planner role in plan mode, with per-role reasoning effort and Web UI configuration.","cmd":"dsh plugin --profile web add @snowamberx/dsh-role-router","href":"/p/SnowAmberX/dsh-role-router/"},{"cat":"model","tag":"Models & Providers","dl":989,"stars":2,"added":"2026-08-29","npm":1,"name":"dsh-llm-subscription","owner":"DavidRm1911","short":"dsh-llm-subscription","slug":"DavidRm1911/dsh-llm-subscription","desc":"Adds Claude, Gemini, and a local Ollama model to DSH's native model picker, using your existing Claude Code / Antigravity CLI logins instead of a metered API key, with a working reasoning-effort selector for Claude.","cmd":"dsh plugin --profile web add dsh-llm-subscription","href":"/p/DavidRm1911/dsh-llm-subscription/"},{"cat":"model","tag":"Models & Providers","dl":987,"stars":4,"added":"2026-09-19","npm":1,"name":"dsh-glm-mode","owner":"hoyyang","short":"dsh-glm-mode","slug":"hoyyang/dsh-glm-mode","desc":"GLM Mode agent preset for zhipuai/glm-5.3-flash: PTC/Code Mode tool presentation, a reasoning loop guard and a tool spin guard (live-incident driven), and GLM-specific auto-compaction at 75%/22%.","cmd":"dsh plugin --profile web add dsh-glm-mode","href":"/p/hoyyang/dsh-glm-mode/"},{"cat":"model","tag":"Models & Providers","dl":979,"stars":2,"added":"2026-10-19","npm":1,"name":"dsh-opencode-bridge","owner":"Vikrant-Aleph","short":"dsh-opencode-bridge","slug":"Vikrant-Aleph/dsh-opencode-bridge","desc":"OpenCode free models for DSH with dynamic model-list refresh, optional HTTP(S)/SOCKS proxy failover, a fail-closed tool bridge and offline agent-scoped compatibility auditing.","cmd":"dsh plugin --profile web add dsh-opencode-bridge","href":"/p/Vikrant-Aleph/dsh-opencode-bridge/"},{"cat":"model","tag":"Models & Providers","dl":975,"stars":6,"added":"2026-08-17","npm":1,"name":"dsh-codex-connect-plus","owner":"stoneface10","short":"dsh-codex-connect-plus","slug":"stoneface10/dsh-codex-connect-plus","desc":"Adds ChatGPT/Codex OAuth-backed Codex models and gpt-image-2 generation/editing to DSH without requiring an OpenAI Platform API key.","cmd":"dsh plugin --profile web add dsh-codex-connect-plus","href":"/p/stoneface10/dsh-codex-connect-plus/"},{"cat":"model","tag":"Models & Providers","dl":966,"stars":2,"added":"2026-09-03","npm":1,"name":"dsh-provider-veark","owner":"IcedWatermelonJuice","short":"dsh-provider-veark","slug":"IcedWatermelonJuice/dsh-provider-veark","desc":"Volcengine Ark Coding Plan LLM provider for DeepSeek Harness: provider-scoped PDF and image input, with Responses API streaming support.","cmd":"dsh plugin --profile web add @icedcola/dsh-provider-veark","href":"/p/IcedWatermelonJuice/dsh-provider-veark/"},{"cat":"model","tag":"Models & Providers","dl":966,"stars":0,"added":"2026-09-26","npm":1,"name":"dsh-more-models-thinking-level","owner":"Henta111","short":"dsh-more-models-thinking-level","slug":"Henta111/dsh-more-models-thinking-level","desc":"Per-model reasoning effort (off/minimal/low/medium/high/xhigh) for GPT, Codex, Gemini and OpenAI-compatible models. Installs a helper, not a runtime adapter: run enable-capabilities.ps1 once per profile (Windows) and restart — it declares the levels in ~/.dsh/settings.yaml, with a disable script and a backup to revert.","cmd":"dsh plugin --profile web add dsh-more-models-thinking-level","href":"/p/Henta111/dsh-more-models-thinking-level/"},{"cat":"model","tag":"Models & Providers","dl":961,"stars":0,"added":"2026-09-22","npm":1,"name":"dsh-chatgpt-oauth","owner":"zhangnan","short":"dsh-chatgpt-oauth","slug":"zhangnan/dsh-chatgpt-oauth","desc":"Sign in with a ChatGPT account and view Codex subscription usage directly in DSH Web's model settings, with browser or device-code OAuth.","cmd":"dsh plugin --profile web add dsh-chatgpt-oauth","href":"/p/zhangnan/dsh-chatgpt-oauth/"},{"cat":"model","tag":"Models & Providers","dl":933,"stars":4,"added":"2026-08-19","npm":1,"name":"dsh-model-capabilities","owner":"WJZ-P","short":"dsh-model-capabilities","slug":"WJZ-P/dsh-model-capabilities","desc":"Adds an input-modality selector to custom model settings in the DeepSeek Harness Web UI.","cmd":"dsh plugin --profile web add dsh-model-capability","href":"/p/WJZ-P/dsh-model-capabilities/"},{"cat":"model","tag":"Models & Providers","dl":931,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-ai-providers#runtime","owner":"Firefox2100","short":"dsh-ai-providers#runtime","slug":"Firefox2100/dsh-ai-providers--packages-dsh-ai-providers","desc":"AI provider runtime and configuration UI for shared credentials and embedding, reranking, speech, and image generation services in DSH.","cmd":"dsh plugin --profile web add @dsh-ai-providers/runtime","href":"/p/Firefox2100/dsh-ai-providers--packages-dsh-ai-providers/"},{"cat":"model","tag":"Models & Providers","dl":928,"stars":5,"added":"2026-08-27","npm":1,"name":"dsh-http-proxy","owner":"elizax","short":"dsh-http-proxy","slug":"elizax/dsh-http-proxy","desc":"Wraps globalThis.fetch to route DeepSeek Harness model-API requests through an HTTP/SOCKS proxy by target domain, leaving all other requests on the direct connection, without modifying Harness source.","cmd":"dsh plugin --profile web add dsh-http-proxy","href":"/p/elizax/dsh-http-proxy/"},{"cat":"model","tag":"Models & Providers","dl":916,"stars":0,"added":"2026-09-13","npm":1,"name":"dsh-llm-api-pool","owner":"bainianlaoyao","short":"dsh-llm-api-pool","slug":"bainianlaoyao/dsh-llm-api-pool","desc":"Pools several OpenCode Go API keys and hot-switches each request to the least-used one, with official usage and balance lookup plus a graphical settings page.","cmd":"dsh plugin --profile web add dsh-llm-api-pool","href":"/p/bainianlaoyao/dsh-llm-api-pool/"},{"cat":"model","tag":"Models & Providers","dl":909,"stars":4,"added":"2026-09-07","npm":1,"name":"dsh-multi-model-orchestrator","owner":"Bazley13","short":"dsh-multi-model-orchestrator","slug":"Bazley13/dsh-multi-model-orchestrator","desc":"Multi-model orchestrator: the main brain decomposes complex tasks and dispatches subtasks to GLM / Kimi / Qwen sub-agents by each model's strengths, with per-model token usage.","cmd":"dsh plugin --profile web add dsh-multi-model-orchestrator","href":"/p/Bazley13/dsh-multi-model-orchestrator/"},{"cat":"model","tag":"Models & Providers","dl":908,"stars":1,"added":"2026-09-02","npm":1,"name":"dsh-kernel-mesh","owner":"oppnc","short":"dsh-kernel-mesh","slug":"oppnc/dsh-kernel-mesh","desc":"Registers Kimi, Grok, Codex, and MiniMax as DeepSeek Harness model routes, vendor subagent recipes, and kernel_status / kernel_run / kernel_switch tools.","cmd":"dsh plugin --profile web add dsh-kernel-mesh","href":"/p/oppnc/dsh-kernel-mesh/"},{"cat":"model","tag":"Models & Providers","dl":899,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-ai-providers#openai","owner":"Firefox2100","short":"dsh-ai-providers#openai","slug":"Firefox2100/dsh-ai-providers--packages-dsh-ai-openai","desc":"OpenAI provider for language models, embeddings, text-to-speech, speech-to-text, and image generation in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.","cmd":"dsh plugin --profile web add @dsh-ai-providers/openai","href":"/p/Firefox2100/dsh-ai-providers--packages-dsh-ai-openai/"},{"cat":"model","tag":"Models & Providers","dl":892,"stars":1,"added":"2026-10-17","npm":1,"name":"dsh-image-bridge","owner":"kkj-luna","short":"dsh-image-bridge","slug":"kkj-luna/dsh-image-bridge","desc":"Text-to-image and image-to-image for a model that cannot draw, through any OpenAI-compatible image API, with multiple providers and an automatic fallback model.","cmd":"dsh plugin --profile web add kkj-luna-dsh-image-bridge","href":"/p/kkj-luna/dsh-image-bridge/"},{"cat":"model","tag":"Models & Providers","dl":886,"stars":0,"added":"2026-09-11","npm":1,"name":"dsh-plugin-tokenmarket","owner":"FitBBC","short":"dsh-plugin-tokenmarket","slug":"FitBBC/dsh-plugin-tokenmarket","desc":"Adds Token Market as an OpenAI-compatible model provider with DeepSeek V4 Pro, Kimi K3, and GLM-5.3.","cmd":"dsh plugin --profile web add dsh-plugin-tokenmarket","href":"/p/FitBBC/dsh-plugin-tokenmarket/"},{"cat":"model","tag":"Models & Providers","dl":886,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-connect-opencode","owner":"serra006","short":"dsh-connect-opencode","slug":"serra006/dsh-connect-opencode","desc":"Expose every free model from a local opencode serve catalog — all providers, including your own custom ones — to DeepSeek Harness's model picker, with OpenCode's native tools denied so execution stays in DSH.","cmd":"dsh plugin --profile web add dsh-connect-opencode","href":"/p/serra006/dsh-connect-opencode/"},{"cat":"model","tag":"Models & Providers","dl":886,"stars":0,"added":"2026-08-30","npm":1,"name":"dsh-codex","owner":"yoshino-xiao7","short":"dsh-codex","slug":"yoshino-xiao7/dsh-codex","desc":"Community Codex provider for DeepSeek Harness with ChatGPT OAuth, Codex models, image input, quota display, per-session Fast and transport controls, and safe stream recovery.","cmd":"dsh plugin --profile web add dsh-codex-community","href":"/p/yoshino-xiao7/dsh-codex/"},{"cat":"model","tag":"Models & Providers","dl":885,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-ai-providers#anthropic","owner":"Firefox2100","short":"dsh-ai-providers#anthropic","slug":"Firefox2100/dsh-ai-providers--packages-dsh-ai-anthropic","desc":"Anthropic provider using the native Messages API for language models in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.","cmd":"dsh plugin --profile web add @dsh-ai-providers/anthropic","href":"/p/Firefox2100/dsh-ai-providers--packages-dsh-ai-anthropic/"},{"cat":"model","tag":"Models & Providers","dl":884,"stars":14,"added":"2026-08-16","npm":1,"name":"dsh-codex-oauth","owner":"WNJXYK","short":"dsh-codex-oauth","slug":"WNJXYK/dsh-codex-oauth","desc":"Use a ChatGPT/Codex subscription in DeepSeek Harness with GPT models, image generation, web search, subscription quota reporting, model and feature controls, and browser or device-code OAuth sign-in.","cmd":"dsh plugin --profile web add @wnjxyk/dsh-codex-oauth","href":"/p/WNJXYK/dsh-codex-oauth/"},{"cat":"model","tag":"Models & Providers","dl":873,"stars":2,"added":"2026-08-23","npm":1,"name":"dsh-model-router","owner":"welsione","short":"dsh-model-router","slug":"welsione/dsh-model-router","desc":"Unified model routing for DeepSeek Harness: one logical ModelID over multiple providers with first-token failover and cooldown, health-aware candidate ranking, three tiers (tier1/tier2/tier3) auto-selected by purpose, per-candidate reasoning effort, and a settings-page management panel.","cmd":"dsh plugin --profile web add @welsione/dsh-model-router","href":"/p/welsione/dsh-model-router/"},{"cat":"model","tag":"Models & Providers","dl":862,"stars":1,"added":"2026-08-18","npm":1,"name":"dsh-llm-failover","owner":"HB00","short":"dsh-llm-failover","slug":"HB00/dsh-llm-failover","desc":"Automatic provider failover on rate limits or quota exhaustion: switch between providers with configurable per-provider models, a cooldown, and a permanent last-entry fallback.","cmd":"dsh plugin --profile web add dsh-llm-failover","href":"/p/HB00/dsh-llm-failover/"},{"cat":"model","tag":"Models & Providers","dl":855,"stars":3,"added":"2026-08-15","npm":1,"name":"dsh-model-sync","owner":"jiay98528-dev","short":"dsh-model-sync","slug":"jiay98528-dev/dsh-model-sync","desc":"Writes live provider model lists into DSH settings and shows 5h/7d plan windows or metered balance for the current session model.","cmd":"dsh plugin --profile web add dsh-model-sync","href":"/p/jiay98528-dev/dsh-model-sync/"},{"cat":"model","tag":"Models & Providers","dl":852,"stars":4,"added":"2026-10-17","npm":1,"name":"dsh-wtq-pool","owner":"chengzhi-c","short":"dsh-wtq-pool","slug":"chengzhi-c/dsh-wtq-pool","desc":"Brings the WorkBuddy, Trae and Qoder desktop logins on this machine into DeepSeek Harness as OpenAI-compatible local endpoints, with an account pool, automatic account switching when WorkBuddy is rate limited, and a settings panel.","cmd":"dsh plugin --profile web add dsh-wtq-pool","href":"/p/chengzhi-c/dsh-wtq-pool/"},{"cat":"model","tag":"Models & Providers","dl":841,"stars":6,"added":"2026-08-15","npm":1,"name":"dsh-plugin-codex","owner":"wss534857356","short":"dsh-plugin-codex","slug":"wss534857356/dsh-plugin-codex","desc":"Codex App Server model provider using a local Codex login, with session reuse, Harness tool bridging, native action traces, and durable generated-image projection.","cmd":"dsh plugin --profile web add dsh-llm-codex-app-server","href":"/p/wss534857356/dsh-plugin-codex/"},{"cat":"model","tag":"Models & Providers","dl":839,"stars":3,"added":"2026-08-17","npm":1,"name":"dsh-plugin-weaknet-adaptor","owner":"jiay98528-dev","short":"dsh-plugin-weaknet-adaptor","slug":"jiay98528-dev/dsh-plugin-weaknet-adaptor","desc":"Weak-network adaptor: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, and degraded-mode token economy, with a bilingual (zh/en) settings page.","cmd":"dsh plugin --profile web add dsh-plugin-weaknet-adaptor","href":"/p/jiay98528-dev/dsh-plugin-weaknet-adaptor/"},{"cat":"model","tag":"Models & Providers","dl":826,"stars":0,"added":"2026-08-29","npm":1,"name":"dsh-better-model-setting","owner":"HiSeax","short":"dsh-better-model-setting","slug":"HiSeax/dsh-better-model-setting","desc":"Replaces the official Models settings page with provider lifecycle management, per-model reasoning effort tiers, retry overrides, drag reorder and upstream model sync.","cmd":"dsh plugin --profile web add dsh-better-model-setting","href":"/p/HiSeax/dsh-better-model-setting/"},{"cat":"model","tag":"Models & Providers","dl":825,"stars":2,"added":"2026-10-14","npm":1,"name":"dsh-model-gateway","owner":"Leafyezi233","short":"dsh-model-gateway","slug":"Leafyezi233/dsh-model-gateway","desc":"Exposes the models already configured in DeepSeek Harness through an OpenAI-compatible gateway, so other local projects can call them with any standard OpenAI client. Multiple provider candidates share one named group with ordered, balanced or random dispatch; upstream failures before any output switch to the next candidate transparently, and rate-limited requests are retried after the provider's backoff. Per-candidate call statistics (attempts, answers, failures, token/TTFT totals) appear as badges in the settings page, and daily aggregates persist to a local file with a 30-day heatmap and trend view. Until you create a key in the UI, the endpoint accepts calls from anyone who can reach it; keys (stored as SHA-256 hashes) then turn authentication on, and the endpoint stays locked even after the last key is revoked. Exposing the optional LAN listener without a key leaves the port open to the whole network. Runs on DSH 0.1.2-rc.1 through 0.1.7-alpha.1 and later.","cmd":"dsh plugin --profile web add @leaf233/dsh-model-gateway","href":"/p/Leafyezi233/dsh-model-gateway/"},{"cat":"model","tag":"Models & Providers","dl":824,"stars":1,"added":"2026-08-18","npm":1,"name":"dsh-plugin-dit","owner":"cuboteam","short":"dsh-plugin-dit","slug":"cuboteam/dsh-plugin-dit","desc":"DIT.ai provider bundle for DeepSeek Harness: installs 29 OpenAI Chat Completions models and 10 Anthropic Messages models from one DIT_API_KEY, with protocol-specific thinking configuration.","cmd":"dsh plugin --profile web add dsh-plugin-dit","href":"/p/cuboteam/dsh-plugin-dit/"},{"cat":"model","tag":"Models & Providers","dl":821,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-ai-providers#localai","owner":"Firefox2100","short":"dsh-ai-providers#localai","slug":"Firefox2100/dsh-ai-providers--packages-dsh-ai-localai","desc":"LocalAI provider for language models, embeddings, reranking, speech, and image generation with LocalAI-specific controls in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.","cmd":"dsh plugin --profile web add @dsh-ai-providers/localai","href":"/p/Firefox2100/dsh-ai-providers--packages-dsh-ai-localai/"},{"cat":"model","tag":"Models & Providers","dl":802,"stars":4,"added":"2026-08-24","npm":1,"name":"dsh-agy-provider","owner":"darkings","short":"dsh-agy-provider","slug":"darkings/dsh-agy-provider","desc":"DSH model provider for the locally authenticated AGY CLI: Gemini/Claude model discovery, independent reasoning effort, DSH-owned tools, bounded context and tool-result handling, and Windows-safe streaming. Report problems in GitHub Issues: https://github.com/darkings/dsh-agy-provider/issues.","cmd":"dsh plugin --profile web add dsh-agy-provider","href":"/p/darkings/dsh-agy-provider/"},{"cat":"model","tag":"Models & Providers","dl":798,"stars":0,"added":"2026-10-13","npm":1,"name":"dsh-antigravity-oauth","owner":"aa2246740","short":"dsh-antigravity-oauth","slug":"aa2246740/dsh-antigravity-oauth","desc":"Unofficial Gemini Cloud Code Assist OAuth integration with isolated account storage; carries account-ban risk.","cmd":"dsh plugin --profile web add dsh-antigravity-oauth","href":"/p/aa2246740/dsh-antigravity-oauth/"},{"cat":"model","tag":"Models & Providers","dl":787,"stars":1,"added":"2026-08-27","npm":1,"name":"dsh-model-management","owner":"sharewiner","short":"dsh-model-management","slug":"sharewiner/dsh-model-management","desc":"Manages the default DSH model, provider and model visibility, and optional OpenAI Responses web search.","cmd":"dsh plugin --profile web add @sharewiner/dsh-model-management","href":"/p/sharewiner/dsh-model-management/"},{"cat":"model","tag":"Models & Providers","dl":784,"stars":0,"added":"2026-09-18","npm":1,"name":"knyazevai-dsh","owner":"knyazev741","short":"knyazevai-dsh","slug":"knyazev741/knyazevai-dsh","desc":"Adds the KnyazevAI API provider and its DeepSeek, GLM, and MiniMax model catalog to DeepSeek Harness.","cmd":"dsh plugin --profile web add @knyazevai/dsh-provider","href":"/p/knyazev741/knyazevai-dsh/"},{"cat":"model","tag":"Models & Providers","dl":776,"stars":0,"added":"2026-10-19","npm":1,"name":"dsh-connect-minimaxcode","owner":"JeffTsuiCUG","short":"dsh-connect-minimaxcode","slug":"JeffTsuiCUG/dsh-connect-minimaxcode","desc":"Connects the MiniMax Code models to DSH - reusing the desktop app's sign-in or signing in on its own - with Anthropic-compatible model access, a live model catalog, the daily check-in that grants the free credits, and a credit balance that follows the model you selected.","cmd":"dsh plugin --profile web add dsh-connect-minimaxcode","href":"/p/JeffTsuiCUG/dsh-connect-minimaxcode/"},{"cat":"model","tag":"Models & Providers","dl":772,"stars":2,"added":"2026-08-21","npm":1,"name":"dsh-nl-model-switch","owner":"passingby000","short":"dsh-nl-model-switch","slug":"passingby000/dsh-nl-model-switch","desc":"Switch the current DSH session's model with a natural-language sentence, on web, TUI, or IM bridges (WeChat, Feishu), without touching the panel.","cmd":"dsh plugin --profile web add dsh-nl-model-switch","href":"/p/passingby000/dsh-nl-model-switch/"},{"cat":"model","tag":"Models & Providers","dl":755,"stars":1,"added":"2026-10-16","npm":1,"name":"dsh-model-kit","owner":"PerseusNana7mi","short":"dsh-model-kit","slug":"PerseusNana7mi/dsh-model-kit","desc":"Fills missing model parameters from models.dev, imports models from configured providers, and writes per-field overrides for built-in models, with prices in USD or native CNY set as manual rates or a reference price times a multiplier.","cmd":"dsh plugin --profile web add dsh-model-kit","href":"/p/PerseusNana7mi/dsh-model-kit/"},{"cat":"model","tag":"Models & Providers","dl":728,"stars":1,"added":"2026-09-20","npm":1,"name":"deepseek-harness-desktop-ultra#dsh-plugin-ai-switch","owner":"ijry","short":"DeepSeek-Harness-Desktop-Ultra#dsh-plugin-ai-switch","slug":"ijry/DeepSeek-Harness-Desktop-Ultra--plugins-dsh-plugin-ai-switch","desc":"Pool AI provider accounts per platform and route them through a local loopback proxy that bridges the OpenAI, OpenAI-Responses, Anthropic and Gemini protocols, then write the proxy into Codex, Claude Code, Gemini CLI, Grok, OpenCode, OpenClaw and Hermes config files with snapshot-and-rollback safe writes; registers no agent tools.","cmd":"dsh plugin --profile web add dsh-plugin-ai-switch","href":"/p/ijry/DeepSeek-Harness-Desktop-Ultra--plugins-dsh-plugin-ai-switch/"},{"cat":"model","tag":"Models & Providers","dl":721,"stars":3,"added":"2026-08-28","npm":1,"name":"dsh-qwen38-compaction-fix","owner":"zhubaohi","short":"dsh-qwen38-compaction-fix","slug":"zhubaohi/dsh-qwen38-compaction-fix","desc":"Compaction fix for NInfer-hosted qwen3.8-27b gateways: disables thinking on dsh context-compaction and session-title calls so xhigh reasoning stops burning the whole output budget; the same idea applies to other launch methods, this package targets NInfer only.","cmd":"dsh plugin --profile web add dsh-qwen38-ninfer-compaction-fix","href":"/p/zhubaohi/dsh-qwen38-compaction-fix/"},{"cat":"model","tag":"Models & Providers","dl":713,"stars":6,"added":"2026-08-24","npm":1,"name":"dsh-plugins#think-level","owner":"CREAIT-nl","short":"dsh-plugins#think-level","slug":"CREAIT-nl/dsh-plugins--think-level","desc":"A thinking level stored per provider and model, so reasoning effort outlives the session it was set in and also reaches subagents, which dsh never asks. The in-session picker still wins, and a model with no row keeps its provider default.","cmd":"dsh plugin --profile web add @creait/dsh-think-level","href":"/p/CREAIT-nl/dsh-plugins--think-level/"},{"cat":"model","tag":"Models & Providers","dl":711,"stars":15,"added":"2026-10-12","npm":1,"name":"dsh-opencode-xdbridge","owner":"XDTrees","short":"dsh-opencode-xdbridge","slug":"XDTrees/dsh-opencode-xdbridge","desc":"Adds OpenCode Zen free models to DeepSeek Harness as one provider, backed by a managed, isolated OpenCode runtime, with a Settings page that lists each model and tests it.","cmd":"dsh plugin --profile web add dsh-opencode-xdbridge","href":"/p/XDTrees/dsh-opencode-xdbridge/"},{"cat":"model","tag":"Models & Providers","dl":668,"stars":6,"added":"2026-08-24","npm":1,"name":"dsh-plugins#gen-limit","owner":"CREAIT-nl","short":"dsh-plugins#gen-limit","slug":"CREAIT-nl/dsh-plugins--gen-limit","desc":"Per provider/model generation concurrency, with a settings card: a cap on how many sessions may stream at once, enforced at the stream and again at subagent spawn, where a fan-out past the cap waits in a FIFO queue instead of failing.","cmd":"dsh plugin --profile web add @creait/dsh-gen-limit","href":"/p/CREAIT-nl/dsh-plugins--gen-limit/"},{"cat":"model","tag":"Models & Providers","dl":666,"stars":1,"added":"2026-10-19","npm":1,"name":"dsh-workbuddy2api-panel","owner":"jerry9692","short":"dsh-workbuddy2api-panel","slug":"jerry9692/dsh-workbuddy2api-panel","desc":"Reads a running workbuddy2api-panel over its HTTP API and syncs its models into the DSH model picker with credit multipliers, CN/international realm labels and per-model reasoning-effort levels; also shows remaining credits and usage in a settings page and a sidebar badge.","cmd":"dsh plugin --profile web add dsh-workbuddy2api-panel","href":"/p/jerry9692/dsh-workbuddy2api-panel/"},{"cat":"model","tag":"Models & Providers","dl":640,"stars":1,"added":"2026-10-17","npm":1,"name":"dsh-connect-opencode-free","owner":"DragonHorizon-xtihc","short":"dsh-connect-opencode-free","slug":"DragonHorizon-xtihc/dsh-connect-opencode-free","desc":"Connect OpenCode Zen free-tier models into DeepSeek Harness. Real-time model discovery, per-model toggle in settings, one-click provider write. No API key required.","cmd":"dsh plugin --profile web add dsh-connect-opencode-free","href":"/p/DragonHorizon-xtihc/dsh-connect-opencode-free/"},{"cat":"model","tag":"Models & Providers","dl":639,"stars":19,"added":"2026-10-17","npm":1,"name":"dsh-official-workbuddy-credit-proxy","owner":"2861292267","short":"DSH-Official-WorkBuddy-Credit-Proxy","slug":"2861292267/DSH-Official-WorkBuddy-Credit-Proxy","desc":"Pools every WorkBuddy account signed in on this machine into one auto-failing-over provider, serving OpenAI Chat, OpenAI Responses and Anthropic Messages from the same pool, with model aliases, usage statistics and scheduled credit automation.","cmd":"dsh plugin --profile web add dsh-rotakit","href":"/p/2861292267/DSH-Official-WorkBuddy-Credit-Proxy/"},{"cat":"model","tag":"Models & Providers","dl":636,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-opencode-go-second","owner":"yfwu2020","short":"dsh-opencode-go-second","slug":"yfwu2020/dsh-opencode-go-second","desc":"Adds an independent OpenCode Go connection with credential settings, manual model discovery, and per-conversation session headers.","cmd":"dsh plugin --profile web add dsh-opencode-go-second","href":"/p/yfwu2020/dsh-opencode-go-second/"},{"cat":"model","tag":"Models & Providers","dl":627,"stars":1,"added":"2026-10-13","npm":1,"name":"dsh-oauth-login","owner":"aa2246740","short":"dsh-oauth-login","slug":"aa2246740/dsh-oauth-login","desc":"Adds subscription OAuth and provider Plan API-key logins through Pi adapters, using a DSH-owned credential store.","cmd":"dsh plugin --profile web add dsh-oauth-login","href":"/p/aa2246740/dsh-oauth-login/"},{"cat":"model","tag":"Models & Providers","dl":625,"stars":0,"added":"2026-10-18","npm":1,"name":"dsh-raccoon-connect","owner":"zhlcba","short":"dsh-raccoon-connect","slug":"zhlcba/dsh-raccoon-connect","desc":"Adds DSH 0.2.x kernel support to the SenseTime XiaoHuanXiong desktop-app models, reusing that app's stored sign-in so no API key is needed.","cmd":"dsh plugin --profile web add dsh-raccoon-connect","href":"/p/zhlcba/dsh-raccoon-connect/"},{"cat":"model","tag":"Models & Providers","dl":606,"stars":3,"added":"2026-09-24","npm":1,"name":"dsh-plugin-freecodego#bundle-latest","owner":"XiangSu-ce","short":"dsh-plugin-freecodego#bundle-latest","slug":"XiangSu-ce/dsh-plugin-freecodego--plugin-packages-freecodego-bundle-latest","desc":"Unofficial FreeCodeGo for DeepSeek Harness: DeepSeek, Codex and Claude engines over one session and toolchain, with a 0-token free access channel for deepseek-v4.1-flash, deepseek-v4-pro, deepseek-v4-flash-free, glm-5.3-flash, grok-4.6, kimi-k3, nemotron-3-ultra-free, muse-spark-1.3, Qwen 3.8 Flash and mimo-v2.6-flash-free, plus a keyless private-key gateway.","cmd":"dsh plugin --profile web add freecodego","href":"/p/XiangSu-ce/dsh-plugin-freecodego--plugin-packages-freecodego-bundle-latest/"},{"cat":"model","tag":"Models & Providers","dl":591,"stars":2,"added":"2026-10-22","npm":1,"name":"dsh-zcode-plan-bridge","owner":"tangyixiao","short":"dsh-zcode-plan-bridge","slug":"tangyixiao/dsh-zcode-plan-bridge","desc":"Requires the ZCode CLI installed and signed in. Relays the ZCode CLI agent into DeepSeek Harness as a model provider. A resident app-server session streams each turn, and the model catalogue is read from the CLI at runtime, so context windows, image support and provider routes follow the installed CLI and account. Tool permission requests are denied by default; unknown approval or permission methods are always denied, and full-auto requires an explicit opt-in. DSH approval UI does not mediate this separately spawned app-server process, and the policy is not an OS sandbox.","cmd":"dsh plugin --profile web add dsh-zcode-plan-bridge","href":"/p/tangyixiao/dsh-zcode-plan-bridge/"},{"cat":"model","tag":"Models & Providers","dl":561,"stars":1,"added":"2026-10-22","npm":1,"name":"dsh-workbuddy-harness","owner":"bushizhanghan","short":"dsh-workbuddy-harness","slug":"bushizhanghan/dsh-workbuddy-harness","desc":"Brings WorkBuddy's free and paid models (domestic and international) into DSH without the WorkBuddy desktop app; published as @bushizhanghan/dsh-workmate, installable on dsh 0.2.0-rc.2 through 0.2.1 including prereleases.","cmd":"dsh plugin --profile web add @bushizhanghan/dsh-workmate","href":"/p/bushizhanghan/dsh-workbuddy-harness/"},{"cat":"model","tag":"Models & Providers","dl":560,"stars":2,"added":"2026-10-17","npm":1,"name":"dsh-plugins#dsh-opencode2api","owner":"zhiqiangme","short":"dsh-plugins#dsh-opencode2api","slug":"zhiqiangme/dsh-plugins--dsh-opencode2api","desc":"Runs the standalone opencode2api backend (jasonxu114514/opencode2api, Windows x64/ARM64, no Docker or OpenCode CLI) with DSH and on exit stops only the process it launched; its settings card installs, updates or rolls back the backend from checksum-verified GitHub releases, copies the initial admin password and syncs /v1/models into an opencode2api provider with context, vision and reasoning efforts, re-syncing every 10 minutes.","cmd":"dsh plugin --profile web add @zhiqiangme/dsh-opencode2api","href":"/p/zhiqiangme/dsh-plugins--dsh-opencode2api/"},{"cat":"model","tag":"Models & Providers","dl":531,"stars":0,"added":"2026-10-22","npm":1,"name":"dsh-antigravity-acp","owner":"KouzakiUmi","short":"dsh-antigravity-acp","slug":"KouzakiUmi/dsh-antigravity-acp","desc":"Adds the official Google Antigravity ACP agent as a DeepSeek Harness model provider, with tool execution and approval kept in DSH, Node 22.19+ and a signed-in Antigravity account required, a per-model quota pill and a settings page.","cmd":"dsh plugin --profile web add dsh-bundle-antigravity-host","href":"/p/KouzakiUmi/dsh-antigravity-acp/"},{"cat":"model","tag":"Models & Providers","dl":520,"stars":1,"added":"2026-10-16","npm":1,"name":"dsh-llm-opencode-go","owner":"a2580vb","short":"dsh-llm-opencode-go","slug":"a2580vb/dsh-llm-opencode-go","desc":"OpenCode Go in the DeepSeek Harness model list, providing subscription quota display, model discovery, session affinity, and more.","cmd":"dsh plugin --profile web add dsh-llm-opencode-go","href":"/p/a2580vb/dsh-llm-opencode-go/"},{"cat":"model","tag":"Models & Providers","dl":516,"stars":0,"added":"2026-10-18","npm":1,"name":"dsh-connect-trae-models","owner":"DragonHorizon-xtihc","short":"dsh-connect-trae-models","slug":"DragonHorizon-xtihc/dsh-connect-trae-models","desc":"Aggregates all local Trae accounts into one auto-failover model provider, with manual and automated daily check-in, credits and expiry monitoring, and a model selection settings card.","cmd":"dsh plugin --profile web add dsh-connect-trae-models","href":"/p/DragonHorizon-xtihc/dsh-connect-trae-models/"},{"cat":"model","tag":"Models & Providers","dl":496,"stars":1,"added":"2026-10-17","npm":1,"name":"dsh-model-quickslots","owner":"MoruTeaven","short":"dsh-model-quickslots","slug":"MoruTeaven/dsh-model-quickslots","desc":"A row of model preset buttons above the composer: left-click switches the session to that preset's provider, model and reasoning effort, right-click opens an editor for it, and each preset can carry a custom name instead of the model id. The editor reads the session's live model catalog, and presets are stored locally.","cmd":"dsh plugin --profile web add @moruteaven/dsh-model-quickslots","href":"/p/MoruTeaven/dsh-model-quickslots/"},{"cat":"model","tag":"Models & Providers","dl":456,"stars":4,"added":"2026-10-16","npm":1,"name":"dsh-opencode-zen-plugin","owner":"A42Null","short":"dsh-opencode-zen-plugin","slug":"A42Null/dsh-opencode-zen-plugin","desc":"OpenCode Console (Zen) models for DeepSeek Harness: paste a Console API key under Settings → Plugins and the Console's chat models become selectable, with the catalog synced automatically, each model routed to the endpoint the official docs assign, and free *-free models hidden by default because they only run inside the OpenCode client.","cmd":"dsh plugin --profile web add @a42null/dsh-opencode-zen-plugin","href":"/p/A42Null/dsh-opencode-zen-plugin/"},{"cat":"model","tag":"Models & Providers","dl":438,"stars":0,"added":"2026-10-23","npm":1,"name":"dsh-model-http-proxy","owner":"guhanfei-ai","short":"dsh-model-http-proxy","slug":"guhanfei-ai/dsh-model-http-proxy","desc":"Wraps globalThis.fetch to route chosen domains through one or more named HTTP/SOCKS proxies (exact host or *.suffix rules, per-card enable), with global direct rules that override every proxy; unmatched requests keep the host default network, and saved settings apply on the next request without a restart.","cmd":"dsh plugin --profile web add dsh-model-http-proxy","href":"/p/guhanfei-ai/dsh-model-http-proxy/"},{"cat":"model","tag":"Models & Providers","dl":418,"stars":0,"added":"2026-10-16","npm":1,"name":"onekey-models","owner":"du-yuxuan","short":"OneKey-Models","slug":"du-yuxuan/OneKey-Models","desc":"One-click TokenDance gateway access for DeepSeek Harness: OAuth sign-in stores the API key, a live model catalog with per-model visibility, and agent tools for chat, image generation, video generation and typed decisions.","cmd":"dsh plugin --profile web add onekey-models","href":"/p/du-yuxuan/OneKey-Models/"},{"cat":"model","tag":"Models & Providers","dl":413,"stars":0,"added":"2026-10-23","npm":1,"name":"dsh-request-params","owner":"xiaohai-78","short":"dsh-request-params","slug":"xiaohai-78/dsh-request-params","desc":"Add your own parameters to the model requests dsh sends: OpenRouter provider routing and fallback models, reasoning, sampling and custom body fields, and headers, for OpenRouter or any other gateway. Parameters are organized by the channels dsh already has; a live preview shows what each request will carry, and a request log shows what was sent and what the gateway answered.","cmd":"dsh plugin --profile web add dsh-request-params","href":"/p/xiaohai-78/dsh-request-params/"},{"cat":"model","tag":"Models & Providers","dl":389,"stars":0,"added":"2026-10-18","npm":1,"name":"dsh-grok-byapi","owner":"NingYuanLee","short":"dsh-grok-byapi","slug":"NingYuanLee/dsh-grok-byapi","desc":"Grok model provider for DeepSeek Harness with model discovery, image and video generation, text-to-speech tools, and durable local media tasks over an OpenAI-compatible gateway.","cmd":"dsh plugin --profile web add dsh-grok-byapi","href":"/p/NingYuanLee/dsh-grok-byapi/"},{"cat":"model","tag":"Models & Providers","dl":385,"stars":1,"added":"2026-10-17","npm":1,"name":"dsh-model-show","owner":"ken95573","short":"dsh-model-show","slug":"ken95573/dsh-model-show","desc":"Shows Provider/Model in the DSH Web composer model selector trigger; the dropdown list and its search are unchanged.","cmd":"dsh plugin --profile web add dsh-model-show","href":"/p/ken95573/dsh-model-show/"},{"cat":"model","tag":"Models & Providers","dl":377,"stars":1,"added":"2026-10-17","npm":1,"name":"dsh-zed-provider","owner":"RGarrido03","short":"dsh-zed-provider","slug":"RGarrido03/dsh-zed-provider","desc":"Use Zed AI hosted models in DSH.","cmd":"dsh plugin --profile web add dsh-zed-provider","href":"/p/RGarrido03/dsh-zed-provider/"},{"cat":"model","tag":"Models & Providers","dl":372,"stars":0,"added":"2026-10-23","npm":1,"name":"dsh-provider-proxy","owner":"apolenkov","short":"dsh-provider-proxy","slug":"apolenkov/dsh-provider-proxy","desc":"Routes outbound model traffic per provider host or per model ID through chosen proxies, loopback or direct, configured from a Plugins settings page.","cmd":"dsh plugin --profile web add @apolenkov/dsh-provider-proxy","href":"/p/apolenkov/dsh-provider-proxy/"},{"cat":"model","tag":"Models & Providers","dl":371,"stars":0,"added":"2026-10-21","npm":1,"name":"dsh-plugin-team-subagent-control","owner":"Sakana07X","short":"dsh-plugin-team-subagent-control","slug":"Sakana07X/dsh-plugin-team-subagent-control","desc":"Adds per-member model and reasoning-effort routing to DeepSeek Desktop Agent Teams, plus leader-initiated release of a teammate subagent run instance.","cmd":"dsh plugin --profile web add dsh-plugin-team-subagent-control","href":"/p/Sakana07X/dsh-plugin-team-subagent-control/"},{"cat":"model","tag":"Models & Providers","dl":349,"stars":2,"added":"2026-10-17","npm":1,"name":"dsh-thirdapi-thinkingmode","owner":"shuang-ying","short":"dsh-ThirdApi-ThinkingMode","slug":"shuang-ying/dsh-ThirdApi-ThinkingMode","desc":"Reads each third-party endpoint's own model listing and keeps llm-pi-ai's per-model reasoningEfforts in sync, so the composer offers the thinking levels a model actually has.","cmd":"dsh plugin --profile web add dsh-api-thinking","href":"/p/shuang-ying/dsh-ThirdApi-ThinkingMode/"},{"cat":"model","tag":"Models & Providers","dl":340,"stars":11,"added":"2026-09-26","npm":1,"name":"dsh-tap","owner":"taikaikaikai-pixel","short":"dsh-tap","slug":"taikaikaikai-pixel/dsh-tap","desc":"Unofficial upstream bundle for DeepSeek Harness. CodeBuddy gateway with a runtime-synced model catalogue, per-model reasoning efforts, web search/fetch, image generation and a streaming credential bridge, plus TraeWork CN and Qoder CN subscription channels via local translation gateways and a key-type OpenAI-compatible provider registry, all managed from an accordion settings card.","cmd":"dsh plugin --profile web add dsh-tap","href":"/p/taikaikaikai-pixel/dsh-tap/"},{"cat":"model","tag":"Models & Providers","dl":282,"stars":0,"added":"2026-09-18","npm":1,"name":"dsh-model-metadata","owner":"pgjh","short":"dsh-model-metadata","slug":"pgjh/dsh-model-metadata","desc":"DSH plugin: matches a model you declared on a custom gateway to the capability metadata it should have — context window, output cap, reasoning levels and image support — by looking the bare model name up at runtime; the plugin never writes your settings document.","cmd":"dsh plugin --profile web add dsh-model-metadata","href":"/p/pgjh/dsh-model-metadata/"},{"cat":"model","tag":"Models & Providers","dl":259,"stars":3,"added":"2026-10-20","npm":1,"name":"dsh-cliproxyapi-pro","owner":"TinyBOOOOM","short":"dsh-cliproxyapi-pro","slug":"TinyBOOOOM/dsh-cliproxyapi-pro","desc":"Connects one or more CLIProxyAPI (CPA) servers to DeepSeek Harness, discovers each server's models and syncs the selected ones into the model picker, routing each model over its native protocol (Anthropic Messages, OpenAI Responses or OpenAI Chat) with per-model parameter overrides; with a CPA management key it shows per-credential upstream quota in a settings tab and as a badge beside the model picker, and it checks for its own updates and installs them through dshmarket when that is present.","cmd":"dsh plugin --profile web add dsh-cliproxyapi-pro","href":"/p/TinyBOOOOM/dsh-cliproxyapi-pro/"},{"cat":"model","tag":"Models & Providers","dl":255,"stars":0,"added":"2026-10-23","npm":1,"name":"dsh-opencode-connect","owner":"sanser9","short":"dsh-opencode-connect","slug":"sanser9/dsh-opencode-connect","desc":"Brings the free models of a locally installed OpenCode CLI into DSH: starts or reuses a local opencode serve, discovers the live catalog and refreshes it every five minutes, and bridges the session event stream to OpenAI-compatible SSE through a loopback-only shim that validates Host and Origin.","cmd":"dsh plugin --profile web add dsh-opencode-connect","href":"/p/sanser9/dsh-opencode-connect/"},{"cat":"model","tag":"Models & Providers","dl":216,"stars":3,"added":"2026-10-17","npm":1,"name":"dsh-deepseek-web-free","owner":"loyalchiiina","short":"dsh-deepseek-web-free","slug":"loyalchiiina/dsh-deepseek-web-free","desc":"Registers a `deepseek-web` provider that drives your own signed-in chat.deepseek.com account as an extra model in DSH, so no Open Platform API key is needed: the sidebar footer lists your Web conversations, Fork to Workspace opens an independent Harness session that never writes back to the original conversation, native search stays on for the `default` model, and `/clean` is a session toggle that sends only the human text. Fork of y-wi/dsh-deepseek-web, kept working on DSH 0.2.1-alpha.2: the peer ranges are widened so the compatibility gate no longer rejects the whole bundle, the removed settings API is replaced with `ctx.settings.configure()` plus `.volatile()` config fields, the renamed client icons are updated, and an upstream SSE error now surfaces as a real error instead of an empty message that poisoned the session history. The fork also repairs what the rename to `-free` left behind: the session-list route used to derive its suffix from a hard-coded length inherited from the old package name, which had turned every conversation request into a 404 while sign-in still worked; and the sidebar conversation panel now paints on an opaque surface token instead of the host's translucent menu token, which only reads as a menu beside the backdrop blur a body-mounted panel cannot install.","cmd":"dsh plugin --profile web add dsh-deepseek-web-free","href":"/p/loyalchiiina/dsh-deepseek-web-free/"},{"cat":"model","tag":"Models & Providers","dl":216,"stars":2,"added":"2026-10-16","npm":1,"name":"dsh-radeon-cloud-patcher","owner":"zhz8888","short":"dsh-radeon-cloud-patcher","slug":"zhz8888/dsh-radeon-cloud-patcher","desc":"Adds AMD Radeon Cloud as a model provider in DeepSeek Harness, with reasoning-effort levels declared per model. The provider definition ships in the plugin's own patch layer rather than in your profile.","cmd":"dsh plugin --profile web add @zhz8888/dsh-radeon-cloud-patcher","href":"/p/zhz8888/dsh-radeon-cloud-patcher/"},{"cat":"model","tag":"Models & Providers","dl":193,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-cc-switch","owner":"LightingHa","short":"dsh-cc-switch","slug":"LightingHa/dsh-cc-switch","desc":"Brings the providers you already configured in cc-switch into DeepSeek Harness: reads the cc-switch database, converts Claude / Codex / OpenClaw / MCode / Pi entries into llm-pi-ai routes with their API keys, and adds a health check that measures time-to-first-byte and whether each stream completes.","cmd":"dsh plugin --profile web add dsh-cc-switch","href":"/p/LightingHa/dsh-cc-switch/"},{"cat":"model","tag":"Models & Providers","dl":189,"stars":3,"added":"2026-10-20","npm":1,"name":"dsh-opendesign-go","owner":"EliteOtaku","short":"dsh-opendesign-go","slug":"EliteOtaku/dsh-opendesign-go","desc":"OpenDesign Go provider: 12 subscription models over Chat Completions, the real 5-hour and 7-day quota read from the local OpenDesign app, per-model parameters and switches, and multi-account failover.","cmd":"dsh plugin --profile web add dsh-opendesign-go","href":"/p/EliteOtaku/dsh-opendesign-go/"},{"cat":"model","tag":"Models & Providers","dl":138,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-harness-switch","owner":"AlyceStocking","short":"dsh-harness-switch","slug":"AlyceStocking/dsh-harness-switch","desc":"Adds Kimi models to native DSH sessions with per-model selection of the embedded Kimi core or DSH native execution.","cmd":"dsh plugin --profile web add dsh-harness-switch","href":"/p/AlyceStocking/dsh-harness-switch/"},{"cat":"model","tag":"Models & Providers","dl":100,"stars":0,"added":"2026-10-17","npm":1,"name":"dsh-subagent-custom","owner":"xingzhen199186","short":"dsh-subagent-custom","slug":"xingzhen199186/dsh-subagent-custom","desc":"Subagent model control: a Jev classifier labels each turn, and the subagent request itself is rewritten to the provider, model and reasoning effort that the label maps to, at the agent/request hook; a per-session inherit/auto/manual selector, one prompt per role injected ahead of the task, and offline replay of past verdicts.","cmd":"dsh plugin --profile web add dsh-subagent-custom","href":"/p/xingzhen199186/dsh-subagent-custom/"},{"cat":"model","tag":"Models & Providers","dl":93,"stars":2,"added":"2026-10-19","npm":1,"name":"dsh-opencode-zen-free","owner":"HAN102300","short":"dsh-opencode-zen-free","slug":"HAN102300/dsh-opencode-zen-free","desc":"OpenCode Zen free-tier models for DeepSeek Harness with anonymous no-key access, a loopback OpenAI-compatible shim, and real bash/read gate tools.","cmd":"dsh plugin --profile web add dsh-opencode-zen-free","href":"/p/HAN102300/dsh-opencode-zen-free/"},{"cat":"model","tag":"Models & Providers","dl":78,"stars":0,"added":"2026-10-20","npm":1,"name":"dsh-connect-doubao","owner":"Wahwayhale","short":"dsh-connect-doubao","slug":"Wahwayhale/dsh-connect-doubao","desc":"Reuses the sign-in already held by the local Doubao desktop app as a DeepSeek Harness model provider, and adds a read-only quota view for the 5-hour and weekly windows. Windows x64 only: the credential is decrypted with DPAPI.","cmd":"dsh plugin --profile web add dsh-connect-doubao","href":"/p/Wahwayhale/dsh-connect-doubao/"},{"cat":"model","tag":"Models & Providers","dl":61,"stars":0,"added":"2026-10-21","npm":1,"name":"dsh-opencode-cli-bridge","owner":"home-river","short":"dsh-opencode-cli-bridge","slug":"home-river/dsh-opencode-cli-bridge","desc":"Bridge DSH to OpenCode-compatible models via the local OpenCode CLI: native LlmAdapter passthrough, persistent OC sessions with cross-turn tool results, tool mirroring, and a CLI environment check panel. Requires the OpenCode CLI installed locally.","cmd":"dsh plugin --profile web add dsh-opencode-cli-bridge","href":"/p/home-river/dsh-opencode-cli-bridge/"},{"cat":"model","tag":"Models & Providers","dl":58,"stars":1,"added":"2026-10-20","npm":1,"name":"dsh-rustvy","owner":"koliy82","short":"dsh-rustvy","slug":"koliy82/dsh-rustvy","desc":"Vendor marks in the model picker plus a model list kept in step with the provider: mirrors the public catalog and logos to loopback, and regenerates the pi-ai route's models from that route's own endpoint, showing the drift before anything is written.","cmd":"dsh plugin --profile web add dsh-rustvy","href":"/p/koliy82/dsh-rustvy/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":41438,"added":"2026-10-17","npm":0,"name":"dsh-our-free-model","owner":"Ebony-Vinyl","short":"dsh-our-free-model","slug":"Ebony-Vinyl/dsh-our-free-model","desc":"Adds free model lanes to DeepSeek Harness — DeepSeek V4.1 Flash, Kimi K3 and others — with no login, sign-up or API key, plus a local OpenAI-compatible gateway, fallback routing and a usage dashboard.","cmd":"dsh plugin --profile web add github:Ebony-Vinyl/dsh-our-free-model","href":"/p/Ebony-Vinyl/dsh-our-free-model/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":267,"added":"2026-09-04","npm":0,"name":"dsh-workbuddy-xdpool","owner":"XDTrees","short":"dsh-workbuddy-xdpool","slug":"XDTrees/dsh-workbuddy-xdpool","desc":"Merge every locally signed-in WorkBuddy account into DeepSeek Harness as one auto-failing-over model pool (multi-account rotation, live credits, and a model catalog showing per-model credit multipliers and free/night-discount tags).","cmd":"dsh plugin --profile web add github:XDTrees/dsh-workbuddy-xdpool","href":"/p/XDTrees/dsh-workbuddy-xdpool/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":102,"added":"2026-08-27","npm":0,"name":"dsh-authinone","owner":"Stormycry-cryp","short":"dsh-AuthInOne","slug":"Stormycry-cryp/dsh-AuthInOne","desc":"Adds account login, API and custom Provider setup, model switching, image fallback for text-only models, and token/cost attribution to DeepSeek Harness 47f.","cmd":"dsh plugin --profile web add \"https://github.com/Stormycry-cryp/dsh-AuthInOne/releases/download/v0.2.0-alpha.4/dsh-auth-in-one-0.2.0-alpha.4.tgz\"","href":"/p/Stormycry-cryp/dsh-AuthInOne/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":61,"added":"2026-09-19","npm":0,"name":"tinytitan#dsh-tinytitan","owner":"Pummelchen","short":"TinyTitan#dsh-tinytitan","slug":"Pummelchen/TinyTitan--plugins-dsh-tinytitan","desc":"Keeps a local TinyTitan model server reachable from the harness: refreshes the llm-pi-ai route from the installed models and mounts a compaction backend that does not think.","cmd":"dsh plugin --profile web add github:Pummelchen/TinyTitan#path:/plugins/dsh-tinytitan","href":"/p/Pummelchen/TinyTitan--plugins-dsh-tinytitan/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":61,"added":"2026-10-16","npm":0,"name":"multivibe#dsh-multivibe","owner":"thibautrey","short":"multivibe#dsh-multivibe","slug":"thibautrey/multivibe--plugins-dsh-multivibe","desc":"Connect DSH to a MultiVibe gateway and inspect available models and connection status.","cmd":"dsh plugin --profile web add \"https://github.com/thibautrey/multivibe/releases/download/dsh-multivibe-v0.1.0/dsh-multivibe-0.1.0.tgz\"","href":"/p/thibautrey/multivibe--plugins-dsh-multivibe/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":41,"added":"2026-10-16","npm":0,"name":"dsh-workbuddy-trae-qoder-connect","owner":"chengshenyangtai","short":"dsh-workbuddy-trae-qoder-connect","slug":"chengshenyangtai/dsh-workbuddy-trae-qoder-connect","desc":"One DSH plugin that aggregates the models of WorkBuddy (personal multi-account, enterprise and the WorkBuddy AI international edition), Qoder CN and Trae CN into a single model picker with a shared conversation history, live credit multipliers, per-model reasoning effort, the largest context window the international edition declares, and daily check-in where the channel offers one.","cmd":"dsh plugin --profile web add github:chengshenyangtai/dsh-workbuddy-trae-qoder-connect","href":"/p/chengshenyangtai/dsh-workbuddy-trae-qoder-connect/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":32,"added":"2026-10-16","npm":0,"name":"workbuddy-to-dsh#dsh-plugin","owner":"Ianzhyh","short":"workbuddy-to-dsh#dsh-plugin","slug":"Ianzhyh/workbuddy-to-dsh--dsh-plugin","desc":"Registers a local OpenAI-compatible bridge as a native dsh model provider: reuses the models already signed in on the desktop app on this machine, manages the bridge and its local dashboard process, and adds five tools, a /workbuddy command and a nine-tab settings panel. Requires the desktop app to be installed and signed in on the same machine; the bridge binds 127.0.0.1 only.","cmd":"dsh plugin --profile web add github:Ianzhyh/workbuddy-to-dsh#path:/dsh-plugin","href":"/p/Ianzhyh/workbuddy-to-dsh--dsh-plugin/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":32,"added":"2026-08-21","npm":0,"name":"dsh-opencode-zen","owner":"xiaozhe7772222","short":"dsh-opencode-zen","slug":"xiaozhe7772222/dsh-opencode-zen","desc":"Zero-cost access to 6 free large models. No registration, no recharge, 6 free models built-in, multi-key rotation and rate-limit backoff.","cmd":"dsh plugin --profile web add github:xiaozhe7772222/dsh-opencode-zen","href":"/p/xiaozhe7772222/dsh-opencode-zen/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":28,"added":"2026-08-16","npm":0,"name":"dsh-chatgpt-subscription","owner":"songoao25","short":"dsh-chatgpt-subscription","slug":"songoao25/dsh-chatgpt-subscription","desc":"Bind your ChatGPT account via official OAuth and chat with ChatGPT models inside DSH, using your Plus/Pro subscription quota.","cmd":"dsh plugin --profile web add github:songoao25/dsh-chatgpt-subscription","href":"/p/songoao25/dsh-chatgpt-subscription/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":24,"added":"2026-10-16","npm":0,"name":"dsh-factory-provider","owner":"Dalizi2026","short":"dsh-factory-provider","slug":"Dalizi2026/dsh-factory-provider","desc":"Factory (Droid) subscription quota as native DSH model providers, with three protocol routes, your own API key through a loopback gateway, and a settings page for connection status, quota, per-model token statistics and key switching.","cmd":"dsh plugin --profile web add \"https://github.com/Dalizi2026/dsh-factory-provider/releases/latest/download/dsh-factory-provider.tgz\"","href":"/p/Dalizi2026/dsh-factory-provider/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":20,"added":"2026-09-13","npm":0,"name":"dsh-qwen38-local-qol","owner":"Yunado","short":"dsh-qwen38-local-qol","slug":"Yunado/dsh-qwen38-local-qol","desc":"Per-request thinking budgets, a compaction backend, and a settings tab for the local Qwen3.8 line (llama.cpp or NInfer).","cmd":"dsh plugin --profile web add github:Yunado/dsh-qwen38-local-qol","href":"/p/Yunado/dsh-qwen38-local-qol/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":19,"added":"2026-09-07","npm":0,"name":"dsh-model-fix","owner":"TikaFlow","short":"dsh-model-fix","slug":"TikaFlow/dsh-model-fix","desc":"Provides a better model experience, including but not limited to: filling model parameters in multiple ways, improving model compatibility, remembering reasoning efforts, subagents following the parent's model and reasoning effort in real time, and AI self-adjusting reasoning effort.","cmd":"dsh plugin --profile web add \"https://github.com/TikaFlow/dsh-model-fix/releases/latest/download/dsh-model-fix.tgz\"","href":"/p/TikaFlow/dsh-model-fix/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":17,"added":"2026-10-17","npm":0,"name":"dsh-providers-hub","owner":"iJetLi","short":"dsh-providers-hub","slug":"iJetLi/dsh-providers-hub","desc":"Signs in and manages accounts for 16 AI coding providers, plus a cross-provider rotation channel: multi-account pools, automatic credential refresh, credit claiming where the provider offers it, and a local OpenAI-compatible gateway.","cmd":"dsh plugin --profile web add github:iJetLi/dsh-providers-hub","href":"/p/iJetLi/dsh-providers-hub/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":11,"added":"2026-09-24","npm":0,"name":"dsh-0-tools","owner":"ai-yukin","short":"dsh-0-tools","slug":"ai-yukin/dsh-0-tools","desc":"One-click free-model setup for DSH web, built for coding beginners: one-click installer for Windows (install.bat) and macOS/Linux (install.sh, v1.7.0+); four permanently free channels — Zhipu GLM (text + image), SiliconFlow (Qwen3-8B plus 15+ sub-9B models), iFlytek Spark Lite and the OpenRouter free pool, which routes through openrouter/auto and picks from a pool that changes over time; bottom-left setup hint hides once any free model is connected; real-time DeepSeek peak/off-peak pricing reminder; bundled beginner help center.","cmd":"dsh plugin --profile web add github:ai-yukin/dsh-0-tools","href":"/p/ai-yukin/dsh-0-tools/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":10,"added":"2026-10-17","npm":0,"name":"dsh-codearts-auth","owner":"anye-99","short":"dsh-codearts-auth","slug":"anye-99/dsh-codearts-auth","desc":"Signs in to Huawei Cloud CodeArts and registers CodeBuddy, WorkBuddy, LobsterAI, Qoder (global and China), TRAE, Cline, Loomy, Raccoon Work, MiniMax Code, TeleAgent, ZCode, Step Code and Antigravity as LLM providers, with per-provider account pools; several of them also show quota balance and daily check-in in the same panel.","cmd":"dsh plugin --profile web add github:anye-99/dsh-codearts-auth","href":"/p/anye-99/dsh-codearts-auth/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":10,"added":"2026-08-28","npm":0,"name":"dsh-kiro","owner":"dat-lequoc","short":"dsh-kiro","slug":"dat-lequoc/dsh-kiro","desc":"Kiro model provider with Builder ID, Identity Center, Google, GitHub and credential-import sign-in, automatic token and profile refresh, account usage, live model discovery, selectable reasoning efforts, streaming tool calls, provider stop-reason and context-overflow handling, and token accounting that uses Kiro's exact counters when it sends them and otherwise scales the context-usage percentage it does send by the model's advertised window.","cmd":"dsh plugin --profile web add github:dat-lequoc/dsh-kiro","href":"/p/dat-lequoc/dsh-kiro/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":9,"added":"2026-08-21","npm":0,"name":"dsh-openai-oauth","owner":"AdonisSheldon","short":"dsh-openai-oauth","slug":"AdonisSheldon/dsh-openai-oauth","desc":"Connect a ChatGPT account to Codex models in DeepSeek Harness through browser PKCE or device-code OAuth, with automatic token refresh and Web or headless login.","cmd":"dsh plugin --profile web add github:AdonisSheldon/dsh-openai-oauth","href":"/p/AdonisSheldon/dsh-openai-oauth/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":9,"added":"2026-08-15","npm":0,"name":"dsh-llm-ollama","owner":"NOirBRight","short":"dsh-llm-ollama","slug":"NOirBRight/dsh-llm-ollama","desc":"Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.","cmd":"dsh plugin --profile web add github:NOirBRight/dsh-llm-ollama","href":"/p/NOirBRight/dsh-llm-ollama/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":8,"added":"2026-08-19","npm":0,"name":"dsh-subagent-model-router","owner":"CypherNaught-0x","short":"DSH-Subagent-Model-Router","slug":"CypherNaught-0x/DSH-Subagent-Model-Router","desc":"Automatically and intelligently routes each delegated task to the best configured model using aliases, capability tags, and usage guidance—keeping routine work fast and affordable while sending complex work to stronger specialists. Configure your model team in the Web UI or guided setup, run specialists in parallel with reliable result joining, and see the chosen model at a glance in subagent views and inline in Better Sidebar's Tasks tree.","cmd":"dsh plugin --profile web add github:CypherNaught-0x/DSH-Subagent-Model-Router","href":"/p/CypherNaught-0x/DSH-Subagent-Model-Router/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":8,"added":"2026-08-16","npm":0,"name":"dsh-chinese-mode","owner":"dawnliming","short":"dsh-chinese-mode","slug":"dawnliming/dsh-chinese-mode","desc":"Global Chinese mode: a compact pill switch beside the composer that injects a language requirement into any preset's system prompt (complete personas excepted); reply, thinking and tool output each toggle between Chinese and English, and anchored presets are supported.","cmd":"dsh plugin --profile web add github:dawnliming/dsh-chinese-mode","href":"/p/dawnliming/dsh-chinese-mode/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":8,"added":"2026-08-18","npm":0,"name":"dsh-llm-codex","owner":"NOirBRight","short":"dsh-llm-codex","slug":"NOirBRight/dsh-llm-codex","desc":"ChatGPT Codex subscription chat: official OAuth, a Sol/Terra/Luna catalog with Fast rows, live usage limits, and optional search and view_image tools.","cmd":"dsh plugin --profile web add github:NOirBRight/dsh-llm-codex","href":"/p/NOirBRight/dsh-llm-codex/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":7,"added":"2026-09-18","npm":0,"name":"dsh-workbuddy2api","owner":"tearslee","short":"dsh-workbuddy2api","slug":"tearslee/dsh-workbuddy2api","desc":"Supervises a local workbuddy2api gateway process and exposes its models as an LLM provider, reading context windows and reasoning efforts from the gateway's own model endpoint.","cmd":"dsh plugin --profile web add github:tearslee/dsh-workbuddy2api","href":"/p/tearslee/dsh-workbuddy2api/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":7,"added":"2026-08-21","npm":0,"name":"dsh-ccswitch","owner":"upJiang","short":"dsh-ccswitch","slug":"upJiang/dsh-ccswitch","desc":"Adds CC Switch providers and models to DeepSeek Harness, with provider filtering and model-name search.","cmd":"dsh plugin --profile web add github:upJiang/dsh-ccswitch","href":"/p/upJiang/dsh-ccswitch/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":7,"added":"2026-09-20","npm":0,"name":"dsh-think-ultra","owner":"YUEYUEXYS","short":"dsh-think-ultra","slug":"YUEYUEXYS/dsh-think-ultra","desc":"Pins every request to the native max-effort tier and adds a per-model/per-mode reasoning-depth panel with a 0-20 capability slider, isolated Velocity/Apex profiles, and offline reasoning toolboxes. Distributed as an obfuscated build; commercial use allowed, reverse engineering closed.","cmd":"dsh plugin --profile web add github:YUEYUEXYS/dsh-think-ultra","href":"/p/YUEYUEXYS/dsh-think-ultra/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":6,"added":"2026-08-15","npm":0,"name":"dsh-tier-router","owner":"BruceLanLan","short":"dsh-tier-router","slug":"BruceLanLan/dsh-tier-router","desc":"Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent tiering.","cmd":"dsh plugin --profile web add github:BruceLanLan/dsh-tier-router","href":"/p/BruceLanLan/dsh-tier-router/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":6,"added":"2026-10-17","npm":0,"name":"dsh-hyperworkbuddy","owner":"ChaYeWuu","short":"dsh-hyperworkbuddy","slug":"ChaYeWuu/dsh-hyperworkbuddy","desc":"Bring the WorkBuddy accounts signed in on this machine into DSH, managing CN and international accounts separately. Supports automatic failover between accounts, one-click refresh of model catalogs and credits, the CN daily check-in, and a togglable OpenAI-compatible endpoint.","cmd":"dsh plugin --profile web add github:ChaYeWuu/dsh-hyperworkbuddy","href":"/p/ChaYeWuu/dsh-hyperworkbuddy/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":6,"added":"2026-10-17","npm":0,"name":"dsh-workbuddy","owner":"Faide-cyber","short":"dsh-workbuddy","slug":"Faide-cyber/dsh-workbuddy","desc":"Bring WorkBuddy's free and paid models (domestic and international) into DSH — no WorkBuddy desktop app required.","cmd":"dsh plugin --profile web add \"https://github.com/Faide-cyber/dsh-workbuddy/releases/download/v1.0.15/dsh-workbuddy-1.0.15.tgz\"","href":"/p/Faide-cyber/dsh-workbuddy/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":6,"added":"2026-08-15","npm":0,"name":"dsh-claude-cli","owner":"katsos","short":"dsh-claude-cli","slug":"katsos/dsh-claude-cli","desc":"LLM provider that runs the locally installed Claude Code CLI as the model backend, so requests go through an existing Claude subscription instead of a metered API key; native tool calls are bridged over MCP.","cmd":"dsh plugin --profile web add github:katsos/dsh-claude-cli","href":"/p/katsos/dsh-claude-cli/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":6,"added":"2026-08-16","npm":0,"name":"dsh-plugin-subhub","owner":"kinoward","short":"dsh-plugin-subhub","slug":"kinoward/dsh-plugin-subhub","desc":"Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.","cmd":"dsh plugin --profile web add github:kinoward/dsh-plugin-subhub","href":"/p/kinoward/dsh-plugin-subhub/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":6,"added":"2026-09-26","npm":0,"name":"dsh-gemini-pool","owner":"qikairo7","short":"dsh-gemini-pool","slug":"qikairo7/dsh-gemini-pool","desc":"Multi-account Google Gemini provider: picks the account with the most remaining quota, fails over on 429 with exponential cooldown, probes disabled accounts in the background, and ships a Chinese/English settings page.","cmd":"dsh plugin --profile web add \"https://github.com/qikairo7/dsh-gemini-pool/releases/download/v0.7.2/dsh-gemini-pool-0.7.2.tgz\"","href":"/p/qikairo7/dsh-gemini-pool/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":6,"added":"2026-08-15","npm":0,"name":"dsh-llm-newapi","owner":"wenzetan","short":"dsh-llm-newapi","slug":"wenzetan/dsh-llm-newapi","desc":"NewAPI (OpenAI-compatible gateway) LLM provider: registers a `newapi` route with chat-only model discovery, auto-fills model parameters (context window, reasoning effort) from models.dev, and adds a Web settings section for the base URL and API key.","cmd":"dsh plugin --profile web add github:wenzetan/dsh-llm-newapi","href":"/p/wenzetan/dsh-llm-newapi/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":5,"added":"2026-09-07","npm":0,"name":"dsh-model-info-fill","owner":"11zld22","short":"dsh-model-info-fill","slug":"11zld22/dsh-model-info-fill","desc":"Fills missing context window, max tokens, thinking levels, and image input on custom DSH models from models.dev, and lists unmatched models for manual edits.","cmd":"dsh plugin --profile web add github:11zld22/dsh-model-info-fill","href":"/p/11zld22/dsh-model-info-fill/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":5,"added":"2026-09-18","npm":0,"name":"dsh-plugin-adapter","owner":"1624318455","short":"dsh-plugin-adapter","slug":"1624318455/dsh-plugin-adapter","desc":"Exposes OpenCode Zen free models to DeepSeek Harness with no API key, tracking Zen gateway changes.","cmd":"dsh plugin --profile web add github:1624318455/dsh-plugin-adapter","href":"/p/1624318455/dsh-plugin-adapter/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":5,"added":"2026-08-23","npm":0,"name":"dsh-proactive","owner":"beijingwahw","short":"dsh-proactive","slug":"beijingwahw/dsh-proactive","desc":"Proactive multi-model scheduling plugin: multi-source signal intake with dedup and urgency ranking, a four-way execute/defer/dismiss/ask-user decision engine, DAG plan generation with parallel model execution, quality reflection with automatic retry and model switch, long-term memory for task patterns and lessons, and strategy evolution via genetic algorithms with sandboxed evaluation and canary rollout.","cmd":"dsh plugin --profile web add github:beijingwahw/dsh-proactive","href":"/p/beijingwahw/dsh-proactive/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":5,"added":"2026-09-19","npm":0,"name":"dsh-opencode-go-plus","owner":"HaydenSmith1121","short":"dsh-opencode-go-plus","slug":"HaydenSmith1121/dsh-opencode-go-plus","desc":"OpenCode Go subscription models as a DeepSeek Harness provider: re-resolves the live gateway catalog every few minutes, auto-adapts models the built-in table has not seen, and covers streaming, tool calls, image input and subscription usage. A maintained fork of dsh-opencode-go: a clash with the upstream package over the llm-opencode-go settings namespace makes it withdraw quietly instead of failing the whole plugin tree, and an already-claimed opencode-go route makes it serve on opencode-go-plus.","cmd":"dsh plugin --profile web add github:HaydenSmith1121/dsh-opencode-go-plus","href":"/p/HaydenSmith1121/dsh-opencode-go-plus/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":5,"added":"2026-10-13","npm":0,"name":"dsh-commandcode","owner":"Plocr","short":"dsh-commandcode","slug":"Plocr/dsh-commandcode","desc":"Command Code for DSH connects Go / GOAT / Pro / Max subscriptions through llm-pi-ai provider profiles, with model sync previews, favorites and hidden models, per-model reasoning presets, explicit request diagnostics, usage alerts, configuration import/export and web search.","cmd":"dsh plugin --profile web add \"https://github.com/Plocr/dsh-commandcode/releases/latest/download/dsh-commandcode-goat.tgz\"","href":"/p/Plocr/dsh-commandcode/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-09-18","npm":0,"name":"dsh-anthropic-membership","owner":"antonio-mastropaolo","short":"dsh-anthropic-membership","slug":"antonio-mastropaolo/dsh-anthropic-membership","desc":"Sign in to DeepSeek Harness with a Claude Pro/Max membership (no API key), downscale Anthropic request images to a 2000px long edge, slim /compact summarizer payloads, and show 5-hour/weekly plan usage plus DSH message counts.","cmd":"dsh plugin --profile web add github:antonio-mastropaolo/dsh-anthropic-membership","href":"/p/antonio-mastropaolo/dsh-anthropic-membership/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-09-15","npm":0,"name":"dsh-plugin-local-model","owner":"DZQJOKER","short":"dsh-plugin-local-model","slug":"DZQJOKER/dsh-plugin-local-model","desc":"Local model plugin for DeepSeek Harness: manage GGUF models in settings, auto-launch llama.cpp on first message, and auto-unload after 5 minutes of idle time to free VRAM.","cmd":"dsh plugin --profile web add github:DZQJOKER/dsh-plugin-local-model","href":"/p/DZQJOKER/dsh-plugin-local-model/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-08-28","npm":0,"name":"dsh-provider-rate-limit","owner":"jyao-SUSE-power-group","short":"dsh-provider-rate-limit","slug":"jyao-SUSE-power-group/dsh-provider-rate-limit","desc":"Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.","cmd":"dsh plugin --profile web add github:jyao-SUSE-power-group/dsh-provider-rate-limit","href":"/p/jyao-SUSE-power-group/dsh-provider-rate-limit/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-09-08","npm":0,"name":"dsh-model-capabilities","owner":"Kalospacer","short":"dsh-model-capabilities","slug":"Kalospacer/dsh-model-capabilities","desc":"Adds a settings page for declaring per-model reasoning efforts and vision support on pi-ai provider routes.","cmd":"dsh plugin --profile web add \"https://github.com/Kalospacer/dsh-model-capabilities/releases/download/v0.1.0/dsh-model-capabilities-0.1.0.tgz\"","href":"/p/Kalospacer/dsh-model-capabilities/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-10-13","npm":0,"name":"dsh-zcode-cli-proxy","owner":"kyle123740","short":"dsh-zcode-cli-proxy","slug":"kyle123740/dsh-zcode-cli-proxy","desc":"Relays the ZCode CLI (the client-bundled coding agent) into DeepSeek Harness as a model provider: a resident app-server session injects the Start Plan account and signs each request with the OAuth plan token, so model requests burn ZCode Start Plan / Coding Plan quota directly — real streaming, image input, per-session resume, no API key.","cmd":"dsh plugin --profile web add github:kyle123740/dsh-zcode-cli-proxy","href":"/p/kyle123740/dsh-zcode-cli-proxy/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-08-29","npm":0,"name":"dsh-llm-opencode-go","owner":"NOirBRight","short":"dsh-llm-opencode-go","slug":"NOirBRight/dsh-llm-opencode-go","desc":"OpenCode Go subscription chat for DSH with per-model Completions, Responses, or Anthropic protocol selection, model discovery, context, vision and thinking metadata, effort defaults, and usage meters.","cmd":"dsh plugin --profile web add github:NOirBRight/dsh-llm-opencode-go","href":"/p/NOirBRight/dsh-llm-opencode-go/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-08-16","npm":0,"name":"dsh-codex-shim","owner":"OpenTritium","short":"dsh-codex-shim","slug":"OpenTritium/dsh-codex-shim","desc":"Simulates a Codex environment for selected model routes to improve GPT-family model tool-call success.","cmd":"dsh plugin --profile web add github:OpenTritium/dsh-codex-shim","href":"/p/OpenTritium/dsh-codex-shim/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-08-14","npm":0,"name":"dsh-model-router","owner":"superboy911","short":"dsh-model-router","slug":"superboy911/dsh-model-router","desc":"Deterministic keyword routing, allowlisted model switching, and an isolated image_gen channel for DeepSeek Harness.","cmd":"dsh plugin --profile web add github:superboy911/dsh-model-router","href":"/p/superboy911/dsh-model-router/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-08-25","npm":0,"name":"dsh-opencode-models","owner":"wyouwd1","short":"dsh-opencode-models","slug":"wyouwd1/dsh-opencode-models","desc":"Manages OpenCode Zen free-tier and Go-tier models in settings.yaml — fetches the live model listings from opencode.ai, reports configured-versus-live drift per route, and adds or removes entries through four agent tools and an OpenCode Models settings section.","cmd":"dsh plugin --profile web add \"https://github.com/wyouwd1/dsh-opencode-models/releases/latest/download/dsh-opencode-models.tgz\"","href":"/p/wyouwd1/dsh-opencode-models/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-09-15","npm":0,"name":"dsh-deepseek-web","owner":"zgrajdnhj7806-svg","short":"dsh-deepseek-web","slug":"zgrajdnhj7806-svg/dsh-deepseek-web","desc":"Calls your own chat.deepseek.com account as a second model from DSH: ask a question, analyze a file's line range, and check login state, plus a runtime skill and a settings-page login panel.","cmd":"dsh plugin --profile web add github:zgrajdnhj7806-svg/dsh-deepseek-web","href":"/p/zgrajdnhj7806-svg/dsh-deepseek-web/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":4,"added":"2026-10-16","npm":0,"name":"dsh-codebuddy","owner":"zhang-tod","short":"dsh-codebuddy","slug":"zhang-tod/dsh-codebuddy","desc":"Unofficial provider that connects Tencent CodeBuddy open platform models to DeepSeek Harness, with automatic model discovery and a settings page for the API key.","cmd":"dsh plugin --profile web add github:zhang-tod/dsh-codebuddy","href":"/p/zhang-tod/dsh-codebuddy/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-08-15","npm":0,"name":"dsh-models-dev-reasoning","owner":"aerince","short":"dsh-models-dev-reasoning","slug":"aerince/dsh-models-dev-reasoning","desc":"Adds models.dev reasoning levels to unconfigured third-party DeepSeek Harness models.","cmd":"dsh plugin --profile web add github:aerince/dsh-models-dev-reasoning","href":"/p/aerince/dsh-models-dev-reasoning/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-10-17","npm":0,"name":"dsh-ark-coding-provider","owner":"Akiyuki1130","short":"dsh-ark-coding-provider","slug":"Akiyuki1130/dsh-ark-coding-provider","desc":"Unofficial Volcengine Ark Coding Plan LLM provider: registers an `ark-coding` route with 12 models (capacity facts measured per model), multi-account with automatic rotation, a bundled pinned arkcli for the official model catalog and live plan quota, plus a settings wizard and a sidebar usage card.","cmd":"dsh plugin --profile web add github:Akiyuki1130/dsh-ark-coding-provider","href":"/p/Akiyuki1130/dsh-ark-coding-provider/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-10-11","npm":0,"name":"dsh-ollama-cloud","owner":"Asheblog","short":"dsh-ollama-cloud","slug":"Asheblog/dsh-ollama-cloud","desc":"Ollama Cloud provider for DeepSeek Harness: adds the chat route on install, publishes each model's own thinking levels for the composer effort control, keeps the model list current from the endpoint (/api/tags and /api/show, cached for offline boots), shows the account allowance with an API-key field in the Models page and sidebar, and offers Ollama's web search and fetch as selectable DSH web providers.","cmd":"dsh plugin --profile web add \"https://github.com/Asheblog/dsh-ollama-cloud/releases/latest/download/dsh-ollama-cloud.tgz\"","href":"/p/Asheblog/dsh-ollama-cloud/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-08-28","npm":0,"name":"claude-in-dsh","owner":"GeekRicardo","short":"claude-in-dsh","slug":"GeekRicardo/claude-in-dsh","desc":"Hand a DSH web session to the locally installed Claude Code CLI: a per-session engine selector (DSH | Claude Code), Claude models and reasoning effort in the model seat, Claude permission modes in place of the access-mode selector, and permission requests, AskUserQuestion and ExitPlanMode routed to the native DSH approval, question and plan-review cards. The stream is written as native DSH session events, so the built-in transcript, tool cards and nested subagents render it; Claude slash commands merge into the command palette; the CLI is held by a detached broker, so plugin updates and DSH restarts do not interrupt a running turn.","cmd":"dsh plugin --profile web add github:GeekRicardo/claude-in-dsh","href":"/p/GeekRicardo/claude-in-dsh/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-09-23","npm":0,"name":"dsh-openrouter-free-models","owner":"itongxiaojun","short":"dsh-openrouter-free-models","slug":"itongxiaojun/dsh-openrouter-free-models","desc":"Discovers OpenRouter's free models, measures their real speed and context size, and writes them into the DeepSeek Harness model list fastest-first, with speed and context in each display name, plus a Settings section to configure and run it.","cmd":"dsh plugin --profile web add github:itongxiaojun/dsh-openrouter-free-models","href":"/p/itongxiaojun/dsh-openrouter-free-models/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-08-14","npm":0,"name":"dsh-polyglot","owner":"Jesse-njx","short":"dsh-polyglot","slug":"Jesse-njx/dsh-polyglot","desc":"The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.","cmd":"dsh plugin --profile web add github:Jesse-njx/dsh-polyglot","href":"/p/Jesse-njx/dsh-polyglot/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-08-14","npm":0,"name":"dsh-everything-oauth","owner":"kam74515-boop","short":"dsh-everything-oauth","slug":"kam74515-boop/dsh-everything-oauth","desc":"Import local Codex, Grok, Claude, OpenCode, and CC Switch logins into DSH; pick sources and enable models in Settings.","cmd":"dsh plugin --profile web add github:kam74515-boop/dsh-everything-oauth","href":"/p/kam74515-boop/dsh-everything-oauth/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-09-03","npm":0,"name":"dsh-llm-error-retry","owner":"liaoyuqing","short":"dsh-llm-error-retry","slug":"liaoyuqing/dsh-llm-error-retry","desc":"LLM request retry plugin for DeepSeek Harness: when a model request fails with a configured HTTP status code, machine code, or provider field=value match, it sleeps for the per-rule delay and re-issues the request automatically, so subscription quota and rate-limit errors (429 / insufficient_quota) do not interrupt a run.","cmd":"dsh plugin --profile web add \"https://github.com/liaoyuqing/dsh-llm-error-retry/releases/latest/download/dsh-llm-error-retry.tgz\"","href":"/p/liaoyuqing/dsh-llm-error-retry/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-08-29","npm":0,"name":"dsh-llm-commandcode","owner":"NOirBRight","short":"dsh-llm-commandcode","slug":"NOirBRight/dsh-llm-commandcode","desc":"Command Code Provider API chat for DSH with a Host-held API key, discovered model catalog, effort defaults, an optional zero-data-retention header, quota meters, and per-model OpenAI or Anthropic protocol selection.","cmd":"dsh plugin --profile web add github:NOirBRight/dsh-llm-commandcode","href":"/p/NOirBRight/dsh-llm-commandcode/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-09-27","npm":0,"name":"dsh-subagent-model-config","owner":"sequoiayunus-hue","short":"dsh-subagent-model-config","slug":"sequoiayunus-hue/dsh-subagent-model-config","desc":"Settings-UI editor that assigns per-teammate model and reasoning-effort rules for DSH native agent teams, resolved at spawn time by wrapping SubagentRuntime.startContinuable. No official files are modified.","cmd":"dsh plugin --profile web add github:sequoiayunus-hue/dsh-subagent-model-config","href":"/p/sequoiayunus-hue/dsh-subagent-model-config/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":3,"added":"2026-09-11","npm":0,"name":"dsh-llm-acp","owner":"shenkonghui","short":"dsh-llm-acp","slug":"shenkonghui/dsh-llm-acp","desc":"LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) server — Claude Code, Codex, Gemini CLI, Devin and more — with a registry browser, per-server settings UI, lazy authentication, and dynamic model discovery.","cmd":"dsh plugin --profile web add github:shenkonghui/dsh-llm-acp","href":"/p/shenkonghui/dsh-llm-acp/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-21","npm":0,"name":"dsh-multi-agent-gateway","owner":"a1141171521","short":"dsh-multi-agent-gateway","slug":"a1141171521/dsh-multi-agent-gateway","desc":"Adds six AI coding platforms to DSH — OpenCode, Qoder, Qoder CN, TRAE, WorkBuddy and WorkBuddy International — each as its own group in the native model picker, and manages their accounts from one settings page, with daily check-in where the platform has one, credit balance lookups, and retry on another account of the same platform when one is rate-limited. Models carry their credit multiplier where the platform declares one. OpenCode's anonymous free tier works with no credential, and TRAE stays hidden by default until it is enabled in the settings.","cmd":"dsh plugin --profile web add github:a1141171521/dsh-multi-agent-gateway","href":"/p/a1141171521/dsh-multi-agent-gateway/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-17","npm":0,"name":"dsh-chatgpt-subscription","owner":"BaoBao1996121","short":"dsh-chatgpt-subscription","slug":"BaoBao1996121/dsh-chatgpt-subscription","desc":"Adds native Codex OAuth sign-in, main-Agent default model selection, and direct or local-proxy settings for DSH Desktop 0.2.0-rc.2 on Windows.","cmd":"dsh plugin --profile web add \"https://github.com/BaoBao1996121/dsh-chatgpt-subscription/releases/download/v0.1.3/dsh-chatgpt-subscription-0.1.3.tgz\"","href":"/p/BaoBao1996121/dsh-chatgpt-subscription/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-17","npm":0,"name":"dsh-codex-oauth","owner":"callqh","short":"dsh-codex-oauth","slug":"callqh/dsh-codex-oauth","desc":"Adds a Codex sign-in page to DSH settings, driving the built-in llm-pi-ai OAuth flow for browser or device-code login and showing masked account status without a separate provider or credential store.","cmd":"dsh plugin --profile web add github:callqh/dsh-codex-oauth","href":"/p/callqh/dsh-codex-oauth/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-08-14","npm":0,"name":"llm-adaptive","owner":"dylan121322","short":"llm-adaptive","slug":"dylan121322/llm-adaptive","desc":"Adaptive model routing: per-request complexity classification with automatic provider routing.","cmd":"dsh plugin --profile web add github:dylan121322/llm-adaptive","href":"/p/dylan121322/llm-adaptive/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-17","npm":0,"name":"dsh-connect-workbuddy","owner":"ethanweave","short":"dsh-connect-workbuddy","slug":"ethanweave/dsh-connect-workbuddy","desc":"Runs a local OpenAI-compatible gateway so DSH can use the model quota of a logged-in Tencent CodeBuddy (WorkBuddy) account: one-shot installer with SHA256 verification, logon scheduled task with duplicate-launch guard, manage.ps1 for status/start/stop/restart/logs/update/uninstall, and an agent skill that drives setup and troubleshooting.","cmd":"dsh plugin --profile web add github:ethanweave/dsh-connect-workbuddy","href":"/p/ethanweave/dsh-connect-workbuddy/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-08-17","npm":0,"name":"dsh-codex-subscription-pool","owner":"Eve-146T","short":"DSH-CODEX-SUBSCRIPTION-POOL","slug":"Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL","desc":"Use your ChatGPT/Codex subscriptions in DSH, with image generation and web search support.","cmd":"dsh plugin --profile web add github:Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL","href":"/p/Eve-146T/DSH-CODEX-SUBSCRIPTION-POOL/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-08-21","npm":0,"name":"dsh-llm-longcat","owner":"ffyuuu","short":"dsh-llm-longcat","slug":"ffyuuu/dsh-llm-longcat","desc":"LongCat-2.0 LLM adapter: 1M context, binary thinking mode, tool calling, and streaming over the OpenAI-compatible endpoint.","cmd":"dsh plugin --profile web add github:ffyuuu/dsh-llm-longcat","href":"/p/ffyuuu/dsh-llm-longcat/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-08-15","npm":0,"name":"keyringseam","owner":"fieldnote-ops","short":"keyringseam","slug":"fieldnote-ops/keyringseam","desc":"macOS Keychain credential provider that replaces the local-file provider and uses a signed, notarized universal helper.","cmd":"dsh plugin --profile web add github:fieldnote-ops/keyringseam","href":"/p/fieldnote-ops/keyringseam/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-17","npm":0,"name":"deepseek-harness-acp","owner":"Fleey","short":"deepseek-harness-acp","slug":"Fleey/deepseek-harness-acp","desc":"Registers external ACP (Agent Client Protocol) agents such as Codex, Claude Code and Gemini CLI as DSH model providers: maps each agent's thought_level options to the reasoning-effort selector, forwards images when the agent advertises promptCapabilities.image, and routes permission requests to DSH's approval dialog; ships an ACP Agents settings page that imports Zed agent_servers JSON and discovers models.","cmd":"dsh plugin --profile web add github:Fleey/deepseek-harness-acp","href":"/p/Fleey/deepseek-harness-acp/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-20","npm":0,"name":"trae2api-dsh","owner":"FuSheng-cs","short":"Trae2api-dsh","slug":"FuSheng-cs/Trae2api-dsh","desc":"Use TRAE account model quota in dsh, with multi-account management, daily check-in, rotation, usage statistics, reasoning levels and model visibility. Requires Python 3.10+; the first run downloads Python dependencies.","cmd":"dsh plugin --profile web add \"https://github.com/FuSheng-cs/Trae2api-dsh/releases/latest/download/trae2api-dsh.tgz\"","href":"/p/FuSheng-cs/Trae2api-dsh/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-19","npm":0,"name":"dsh-model-settings","owner":"Howthemeaning","short":"dsh-model-settings","slug":"Howthemeaning/dsh-model-settings","desc":"Model settings panel for DeepSeek Harness: set the default model for new sessions, plus separate provider/model/reasoning-effort overrides for subagents and goal rounds, with live reload.","cmd":"dsh plugin --profile web add \"https://github.com/Howthemeaning/dsh-model-settings/releases/download/v0.2.2/dsh-model-settings-0.2.2.tgz\"","href":"/p/Howthemeaning/dsh-model-settings/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-16","npm":0,"name":"dsh-auto-driving","owner":"huhaodong","short":"dsh-auto-driving","slug":"huhaodong/dsh-auto-driving","desc":"Model failover and turn keep-alive for DeepSeek Harness: a request that fails with a model error before any visible output falls through the models of the configured provider groups (then the next provider) until one streams; transient failures retry with backoff under a liveness watchdog, a dead turn self-resumes with templated 「继续」 wake-ups, and an optional full-auto mode auto-answers permission, question and plan approvals with every decision appended to an AUTO-MODE.md audit log.","cmd":"dsh plugin --profile web add github:huhaodong/dsh-auto-driving","href":"/p/huhaodong/dsh-auto-driving/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-17","npm":0,"name":"model-failover-manager","owner":"liaoyuqing","short":"model-failover-manager","slug":"liaoyuqing/model-failover-manager","desc":"Model routing groups for the session model picker: bind a group to a session, and once a model exhausts every retry policy the plugin records the failure with its error code, switches to the next usable model in the group and continues the same turn. Groups carry per-model priority, Beijing-time active windows and expiry dates; subagents inherit their parent session's group and can also pick models or bind their own; models served by dsh-our-free-model retry another account before failing over.","cmd":"dsh plugin --profile web add \"https://github.com/liaoyuqing/model-failover-manager/releases/latest/download/model-failover-manager.tgz\"","href":"/p/liaoyuqing/model-failover-manager/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-08-29","npm":0,"name":"dsh-model-switch","owner":"NOirBRight","short":"dsh-model-switch","slug":"NOirBRight/dsh-model-switch","desc":"Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.","cmd":"dsh plugin --profile web add github:NOirBRight/dsh-model-switch","href":"/p/NOirBRight/dsh-model-switch/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-08-16","npm":0,"name":"dsh-swarm-router","owner":"r600a-code","short":"dsh-swarm-router","slug":"r600a-code/dsh-swarm-router","desc":"Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.","cmd":"dsh plugin --profile web add github:r600a-code/dsh-swarm-router","href":"/p/r600a-code/dsh-swarm-router/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-09-02","npm":0,"name":"dsh-opencode-zen","owner":"randomix777","short":"dsh-opencode-zen","slug":"randomix777/dsh-opencode-zen","desc":"Bring OpenCode Zen free models to DSH: 8 live-discovered providers with zero config, no API key; includes persistent quota tracker with rate-limit detection and reset countdown.","cmd":"dsh plugin --profile web add github:randomix777/dsh-opencode-zen","href":"/p/randomix777/dsh-opencode-zen/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-08-23","npm":0,"name":"dsh-codex-use#dsh-codex-appserver","owner":"seriousz158","short":"dsh-codex-use#dsh-codex-appserver","slug":"seriousz158/dsh-codex-use--packages-dsh-codex-appserver","desc":"Adds OpenAI Codex (ChatGPT) as a selectable DSH provider via the local Codex App Server.","cmd":"dsh plugin --profile web add github:seriousz158/dsh-codex-use#path:/packages/dsh-codex-appserver","href":"/p/seriousz158/dsh-codex-use--packages-dsh-codex-appserver/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-17","npm":0,"name":"dsh-local-model","owner":"songzhiyin","short":"dsh-local-model","slug":"songzhiyin/dsh-local-model","desc":"Registers a local LLM provider that routes model calls to an OpenAI-compatible endpoint or the Ollama native API, with a connection-test card in the Models settings page and no account sign-in.","cmd":"dsh plugin --profile web add github:songzhiyin/dsh-local-model","href":"/p/songzhiyin/dsh-local-model/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-10-17","npm":0,"name":"agnes-ai-for-dsh","owner":"wangyemen","short":"agnes-ai-for-dsh","slug":"wangyemen/agnes-ai-for-dsh","desc":"Agnes AI provider for llm-pi-ai: 4 multimodal chat models declared in the bundle patch, plus image and video generation tools.","cmd":"dsh plugin --profile web add github:wangyemen/agnes-ai-for-dsh","href":"/p/wangyemen/agnes-ai-for-dsh/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-08-27","npm":0,"name":"dsh-claude-driver","owner":"zhangjunjesse","short":"dsh-claude-driver","slug":"zhangjunjesse/dsh-claude-driver","desc":"Run the main session model on a local Claude Code subscription through the official Claude Agent SDK, taking over the llm/stream route for the claude-code provider, with token-level streaming, session resume, and DSH tools bridged in over MCP so they keep DSH sandbox and approval.","cmd":"dsh plugin --profile web add github:zhangjunjesse/dsh-claude-driver","href":"/p/zhangjunjesse/dsh-claude-driver/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":2,"added":"2026-08-29","npm":0,"name":"dsh-model-sync","owner":"zhangyqjiaoshou-oss","short":"dsh-model-sync","slug":"zhangyqjiaoshou-oss/dsh-model-sync","desc":"One-click/auto sync provider model lists against /v1/models endpoint.","cmd":"dsh plugin --profile web add github:zhangyqjiaoshou-oss/dsh-model-sync","href":"/p/zhangyqjiaoshou-oss/dsh-model-sync/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-17","npm":0,"name":"dsh-subagent-role-router","owner":"643048695","short":"dsh-subagent-role-router","slug":"643048695/dsh-subagent-role-router","desc":"Route DSH subagent delegations to configured models with per-role routing for explore, plan and patch subagents, round-robin or random distribution, cross-provider failover, and active-window slicing of fork seeds.","cmd":"dsh plugin --profile web add github:643048695/dsh-subagent-role-router","href":"/p/643048695/dsh-subagent-role-router/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-20","npm":0,"name":"dsh-model-auto-enricher","owner":"66rapper","short":"dsh-model-auto-enricher","slug":"66rapper/dsh-model-auto-enricher","desc":"Model channel auto-enricher for DeepSeek Harness: eliminates manually configuring contextWindow, maxTokens, \\[text, image] multimodal input, and {low, high, max} reasoning effort tiers model by model after adding a provider channel, with live auto-enrichment on save, a Settings UI page, and timestamped backups.","cmd":"dsh plugin --profile web add \"https://github.com/66rapper/dsh-model-auto-enricher/releases/latest/download/dsh-model-auto-enricher.tgz\"","href":"/p/66rapper/dsh-model-auto-enricher/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-20","npm":0,"name":"liquid-dsh-plugin","owner":"architect-xyz","short":"liquid-dsh-plugin","slug":"architect-xyz/liquid-dsh-plugin","desc":"Adds the Liquid Inference auction exchange as a model route, with liquid.auto and its ranking variants, and four tools that read offers, markets, routers and job receipts. Requires a Liquid Inference API key (LIQUID_API_KEY, spend scope).","cmd":"dsh plugin --profile web add github:architect-xyz/liquid-dsh-plugin","href":"/p/architect-xyz/liquid-dsh-plugin/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-18","npm":0,"name":"dsh-reasoning-effort-new","owner":"Ayowait","short":"dsh-reasoning-effort-new","slug":"Ayowait/dsh-reasoning-effort-new","desc":"Fork of dsh-reasoning-effort with a two-level model picker in the composer: a provider list, a model pane that slides out beside it, search, and compact rows, alongside the reasoning-effort slider and its max-level effects.","cmd":"dsh plugin --profile web add github:Ayowait/dsh-reasoning-effort-new","href":"/p/Ayowait/dsh-reasoning-effort-new/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-09-04","npm":0,"name":"dsh-model-router","owner":"bill277048-hash","short":"DSH-model-router","slug":"bill277048-hash/DSH-model-router","desc":"Rule-based multi-provider model routing for DeepSeek Harness with pre-first-token failover, cooldown circuit-breaking, usage accounting, and a status API.","cmd":"dsh plugin --profile web add github:bill277048-hash/DSH-model-router","href":"/p/bill277048-hash/DSH-model-router/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-17","npm":0,"name":"dsh-bifenggang","owner":"ccccwwwxx","short":"dsh-bifenggang","slug":"ccccwwwxx/dsh-bifenggang","desc":"Time-based model routing: a settings panel defines weekday peak and off-peak windows and the provider/model each one uses, the choices are read from the harness registry (API keys and subscription logins alike), and a global switch decides whether that policy sets the model and reasoning effort of every request. The switch is independent per session, each session row carries a light showing its own state, and the settings panel names the model in force right now and why. A day no window matches — every weekend and holiday — uses the primary model of the first plan; the advanced thinking model is a separate axis, used only when a session itself asks for max reasoning.","cmd":"dsh plugin --profile web add github:ccccwwwxx/dsh-bifenggang","href":"/p/ccccwwwxx/dsh-bifenggang/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-09-08","npm":0,"name":"dsh-newapi-video","owner":"chen704290901chen","short":"dsh-newapi-video","slug":"chen704290901chen/dsh-newapi-video","desc":"Call a new-api (one-api style) relay station's video model from the conversation with @-referenced image/video materials, supporting Seedance 2.0 and Happyhorse text-to-video and image-to-video across four relay protocols.","cmd":"dsh plugin --profile web add github:chen704290901chen/dsh-newapi-video","href":"/p/chen704290901chen/dsh-newapi-video/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-13","npm":0,"name":"dsh_gearbox","owner":"ctianye","short":"dsh_gearbox","slug":"ctianye/dsh_gearbox","desc":"Reasoning-effort gear presets for third-party models: 16 vendor/model presets with per-mode custom wire values, written into dsh-llm-pi-ai with pre-write validation and per-rule rejection; per-model switching between OpenAI Chat Completions, OpenAI Responses and Anthropic Messages with automatic route regrouping; plus a composer Optimize button and a settings section that rewrite the input text with a model you pick.","cmd":"dsh plugin --profile web add github:ctianye/dsh_gearbox","href":"/p/ctianye/dsh_gearbox/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-20","npm":0,"name":"dsh-model-orchestrator","owner":"DeZhou123","short":"dsh-model-orchestrator","slug":"DeZhou123/dsh-model-orchestrator","desc":"Two-level model routing: pick the best model group first, then the best channel within that model; a failure switches channel before switching model. Preference mode pins one model across its channels, a status bar under the composer shows the live model, channel health and the day's token usage, and a speed/intelligence report can be imported as the routing prior. Exposes a model_orchestrator tool and a /route command.","cmd":"dsh plugin --profile web add github:DeZhou123/dsh-model-orchestrator","href":"/p/DeZhou123/dsh-model-orchestrator/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-25","npm":1,"name":"dsh-haoba-mode","owner":"FelixJiashengFu","short":"dsh-haoba-mode","slug":"FelixJiashengFu/dsh-haoba-mode","desc":"A gold switch beside the composer that raises every model request to the strongest reasoning effort the current model declares and to its default max output tokens, and adds a system-prompt section asking for exhaustive, self-checked work.","cmd":"dsh plugin --profile web add dsh-haoba-mode","href":"/p/FelixJiashengFu/dsh-haoba-mode/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-17","npm":0,"name":"dsh-orquestrator","owner":"frederico-kluser","short":"dsh-orquestrator","slug":"frederico-kluser/dsh-orquestrator","desc":"Pick the model your subagents run on — with a reasoning-effort ceiling and an output-token cap — enforced in code on every child DSH starts, whichever tool starts it.","cmd":"dsh plugin --profile web add github:frederico-kluser/dsh-orquestrator","href":"/p/frederico-kluser/dsh-orquestrator/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-21","npm":1,"name":"dsh-default-model-lock","owner":"hZsFN","short":"dsh-default-model-lock","slug":"hZsFN/dsh-default-model-lock","desc":"Keeps the shared default model pinned, so switching the model inside a chat no longer rewrites the global default and no longer lowers that default's reasoning effort.","cmd":"dsh plugin --profile web add dsh-model-lock","href":"/p/hZsFN/dsh-default-model-lock/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-09-23","npm":0,"name":"dsh-gateway-models","owner":"itchenshi","short":"dsh-gateway-models","slug":"itchenshi/dsh-gateway-models","desc":"Declares the OpenCode Go and Command Code route wire protocol and endpoint (so the API address never has to be typed), adds the DeepSeek V4.1 models to the OpenCode Go route and puts them first, completes the Command Code model list from its public catalog, and attaches a per-conversation x-opencode-session header to OpenCode requests (fixes 400 MissingSessionID).","cmd":"dsh plugin --profile web add \"https://github.com/itchenshi/dsh-gateway-models/releases/download/v0.2.0/dsh-gateway-models-0.2.0.tgz\"","href":"/p/itchenshi/dsh-gateway-models/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-30","npm":0,"name":"dsh-model-palette","owner":"Jensen-Yao","short":"dsh-model-palette","slug":"Jensen-Yao/dsh-model-palette","desc":"Global Alt+M model command palette for DeepSeek Harness Web: fuzzy search over models and providers, favorites and recents, per-model reasoning effort, provider and model configuration, request retries, capacity presets, and optional OpenRouter image/video generation tools.","cmd":"dsh plugin --profile web add github:Jensen-Yao/dsh-model-palette","href":"/p/Jensen-Yao/dsh-model-palette/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-25","npm":0,"name":"dsh-maestro","owner":"JUNQINGV587","short":"dsh-maestro","slug":"JUNQINGV587/dsh-maestro","desc":"Planner/executor delegation with named roles: a strong planner steers, disposable executor sub-agents (per-role routes and prompts) implement. Default role plus per-delegation override, a global reasoning-effort knob in the composer chip, and a settings page for role management.","cmd":"dsh plugin --profile web add github:JUNQINGV587/dsh-maestro","href":"/p/JUNQINGV587/dsh-maestro/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-22","npm":0,"name":"dsh-workbuddy-codex","owner":"kangjiazhen","short":"dsh-workbuddy-codex","slug":"kangjiazhen/dsh-workbuddy-codex","desc":"Registers the workbuddy model provider by mounting dsh-llm-workbuddy, supervises the local wb2api gateway, and runs a bundled Responses-to-chat-completions bridge so Codex CLI can use the same gateway. Skips work that is already running or already registered, and reports each part through a status tool. Requires a local wb2api gateway and a WorkBuddy account.","cmd":"dsh plugin --profile web add github:kangjiazhen/dsh-workbuddy-codex","href":"/p/kangjiazhen/dsh-workbuddy-codex/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-08","npm":0,"name":"dsh-glm-web","owner":"Lequait","short":"dsh-glm-web","slug":"Lequait/dsh-glm-web","desc":"Unofficial Zhipu Qingyan (chatglm.cn) web provider — run DeepSeek Harness on web-app credits with a login token, streaming and prompt-bridged tool calls included.","cmd":"dsh plugin --profile web add github:Lequait/dsh-glm-web","href":"/p/Lequait/dsh-glm-web/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-18","npm":0,"name":"dsh-llm-agnes","owner":"Liustar214","short":"dsh-llm-agnes","slug":"Liustar214/dsh-llm-agnes","desc":"One-click add Agnes AI free models to DeepSeek Harness.","cmd":"dsh plugin --profile web add github:Liustar214/dsh-llm-agnes","href":"/p/Liustar214/dsh-llm-agnes/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-18","npm":0,"name":"oh-my-dsh","owner":"llmpolska","short":"oh-my-dsh","slug":"llmpolska/oh-my-dsh","desc":"Tiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.","cmd":"dsh plugin --profile web add github:llmpolska/oh-my-dsh","href":"/p/llmpolska/oh-my-dsh/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-22","npm":0,"name":"dsh-model-priority","owner":"mengge237","short":"dsh-model-priority","slug":"mengge237/dsh-model-priority","desc":"Reorder your own models: drag inside a provider card on the Models settings page, or use the Model order section when another plugin already occupies that card. The order is written through the host settings service with a revision check, so the settings page and the model picker stay in sync. The settings left nav can be reordered by drag as well.","cmd":"dsh plugin --profile web add github:mengge237/dsh-model-priority","href":"/p/mengge237/dsh-model-priority/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-18","npm":0,"name":"dsh-llm-cursor","owner":"NOirBRight","short":"dsh-llm-cursor","slug":"NOirBRight/dsh-llm-cursor","desc":"Unofficial Cursor subscription chat: Host-owned CLI session login, a displayed model catalog, and subscription usage rails. Cursor staff treat this class of private-client usage as against ToS.","cmd":"dsh plugin --profile web add github:NOirBRight/dsh-llm-cursor","href":"/p/NOirBRight/dsh-llm-cursor/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-18","npm":0,"name":"dsh-llm-grok","owner":"NOirBRight","short":"dsh-llm-grok","slug":"NOirBRight/dsh-llm-grok","desc":"xAI Grok subscription chat: SuperGrok or X Premium+ OAuth, a displayed model subset, Responses through the Grok CLI proxy, and always-on server-side web_search and x_search.","cmd":"dsh plugin --profile web add github:NOirBRight/dsh-llm-grok","href":"/p/NOirBRight/dsh-llm-grok/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-22","npm":0,"name":"dsh-model-failover","owner":"QGG4588","short":"dsh-model-failover","slug":"QGG4588/dsh-model-failover","desc":"Model failover for DeepSeek Harness: pick one or more providers and the pool becomes every model inside them; when a request fails (rate limit, quota, timeout, server or transport error) the next untried model in the pool retries automatically, and the original error surfaces once the pool is exhausted. Configure from a seat beside the composer model picker or the model_failover tool, with no restart needed.","cmd":"dsh plugin --profile web add \"https://github.com/QGG4588/dsh-model-failover/releases/download/v1.2.2/dsh-model-failover-1.2.2.tgz\"","href":"/p/QGG4588/dsh-model-failover/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-16","npm":0,"name":"dsh-jev-mode","owner":"QI-seven33","short":"dsh-jev-mode","slug":"QI-seven33/dsh-jev-mode","desc":"Optional JEV decision mode with deterministic project reads, bounded semantic selection, native authorization checks and desktop credential settings.","cmd":"dsh plugin --profile web add \"https://github.com/QI-seven33/dsh-jev-mode/releases/download/v0.4.4/dsh-jev-mode-0.4.4.tgz\"","href":"/p/QI-seven33/dsh-jev-mode/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-29","npm":0,"name":"dsh-plugin-subs","owner":"randomix777","short":"dsh-plugin-subs","slug":"randomix777/dsh-plugin-subs","desc":"OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE) with zero-config login and usage dashboards.","cmd":"dsh plugin --profile web add github:randomix777/dsh-plugin-subs","href":"/p/randomix777/dsh-plugin-subs/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-16","npm":0,"name":"dsh-subagent-model-picker","owner":"ringoage","short":"dsh-subagent-model-picker","slug":"ringoage/dsh-subagent-model-picker","desc":"A GUI subagent-model selector beside the main model seat: pick a model and reasoning effort per session, applied to every in-process subagent.","cmd":"dsh plugin --profile web add github:ringoage/dsh-subagent-model-picker","href":"/p/ringoage/dsh-subagent-model-picker/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-22","npm":0,"name":"dsh-workbuddy-connect-community","owner":"tangyixiao","short":"dsh-workbuddy-connect-community","slug":"tangyixiao/dsh-workbuddy-connect-community","desc":"Community-maintained WorkBuddy and WorkBuddy AI model provider using local desktop sign-in, with model discovery and credit display. Built for DSH 0.2.1-rc.2, with a CN compatibility layer that differs from the functy23 fork.","cmd":"dsh plugin --profile web add \"https://github.com/tangyixiao/dsh-workbuddy-connect-community/releases/latest/download/dsh-workbuddy-connect-community.tgz\"","href":"/p/tangyixiao/dsh-workbuddy-connect-community/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-19","npm":0,"name":"dsh-delegation-suite","owner":"wenheguo2","short":"dsh-delegation-suite","slug":"wenheguo2/dsh-delegation-suite","desc":"Ranked subagent delegation: role-based model routing with failover, per-route reasoning effort, model-transparent labels, fork delegation, and a visual route editor.","cmd":"dsh plugin --profile web add \"https://github.com/wenheguo2/dsh-delegation-suite/releases/download/v1.0.0/dsh-delegation-suite-1.0.0.tgz\"","href":"/p/wenheguo2/dsh-delegation-suite/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-17","npm":0,"name":"dsh-antigravity","owner":"WiseXin","short":"dsh-antigravity","slug":"WiseXin/dsh-antigravity","desc":"Google Antigravity and Cloud Code Assist model provider with Gemini 3.8 Flash, sandbox failover, and multi-account quota management.","cmd":"dsh plugin --profile web add github:WiseXin/dsh-antigravity","href":"/p/WiseXin/dsh-antigravity/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-31","npm":0,"name":"dsh-commandcode","owner":"wjf1","short":"dsh-commandcode","slug":"wjf1/dsh-commandcode","desc":"Command Code LLM provider for DSH Desktop: registers the commandcode route with a live model catalog, configurable request and stream-idle timeouts, multi-account rotation on 429/401, plan-aware model filtering, an OAuth login flow and a bilingual usage and billing panel.","cmd":"dsh plugin --profile web add github:wjf1/dsh-commandcode","href":"/p/wjf1/dsh-commandcode/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-10-13","npm":0,"name":"dsh-plugin-simple-pet","owner":"YangShen-SWE","short":"dsh-plugin-simple-pet","slug":"YangShen-SWE/dsh-plugin-simple-pet","desc":"Windows anime companion for DeepSeek balances and Codex quotas, with integrated Codex multi-account OAuth, per-account quota and model management, compact mode and autosaving settings. Optional panel account cycling and separately authorized daily warm-up; multi-account startup/5h-full triggers remain unavailable.","cmd":"dsh plugin --profile web add \"https://github.com/YangShen-SWE/dsh-plugin-simple-pet/releases/latest/download/dsh-plugin-simple-pet.tgz\"","href":"/p/YangShen-SWE/dsh-plugin-simple-pet/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-08-21","npm":0,"name":"dsh-llm-governor","owner":"young-tim","short":"dsh-llm-governor","slug":"young-tim/dsh-llm-governor","desc":"Governs multi-model access, monthly credits, manual/quality/credit/auto routing, failure rerouting, and usage auditing for DSH.","cmd":"dsh plugin --profile web add github:young-tim/dsh-llm-governor","href":"/p/young-tim/dsh-llm-governor/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":1,"added":"2026-09-23","npm":0,"name":"dsh-llm-provider","owner":"Ztyss","short":"dsh-llm-provider","slug":"Ztyss/dsh-llm-provider","desc":"Replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai through a safe-zone download with a one-click enable toggle, and adds provider quota and balance lookups plus a provider management page.","cmd":"dsh plugin --profile web add github:Ztyss/dsh-llm-provider","href":"/p/Ztyss/dsh-llm-provider/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-20","npm":0,"name":"dsh-subagent","owner":"1373700184","short":"dsh-subagent","slug":"1373700184/dsh-subagent","desc":"Registers local Qoder, QoderCN, OpenCode, Pi and CodeBuddy CLIs as DSH subagent backends, with ordered model fallback, live progress, per-run credit display, a settings page, and slash commands. Requires the corresponding CLI installed and logged in.","cmd":"dsh plugin --profile web add github:1373700184/dsh-subagent","href":"/p/1373700184/dsh-subagent/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-18","npm":0,"name":"dsh-multi-model-discussion","owner":"a331266223","short":"dsh-multi-model-discussion","slug":"a331266223/dsh-multi-model-discussion","desc":"Multi-model deliberation pipeline for DeepSeek Harness: independent proposals, blind peer review, program-executed evidence verification, immutable revision and independent acceptance on a fresh context.","cmd":"dsh plugin --profile web add github:a331266223/dsh-multi-model-discussion","href":"/p/a331266223/dsh-multi-model-discussion/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-19","npm":0,"name":"dsh-switch","owner":"a981008","short":"dsh-switch","slug":"a981008/dsh-switch","desc":"Mirrors cc-switch providers and models into DeepSeek Harness the moment they are saved, and shows each provider's plan windows, account balance, or custom usage script in the composer and the settings card.","cmd":"dsh plugin --profile web add github:a981008/dsh-switch","href":"/p/a981008/dsh-switch/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-24","npm":0,"name":"dsh-workbuddy-connect","owner":"AidenOrz","short":"dsh-workbuddy-connect","slug":"AidenOrz/dsh-workbuddy-connect","desc":"Drop-in successor to the now-deleted corrinehu/dsh-workbuddy-connect, keeping its package name, config row id and provider ids so an existing install upgrades in place. Also fixes the 400/11128 channel check by neutralising the DSH identity sentences and scrubbing the product name from system messages, and reads the real Windows client and bundled CLI versions instead of a compiled constant, unlike the functy and community forks. Verified 2026-10-21 on Windows, WorkBuddy 5.8.3, DSH 0.2.1-rc.2.","cmd":"dsh plugin --profile web add github:AidenOrz/dsh-workbuddy-connect","href":"/p/AidenOrz/dsh-workbuddy-connect/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-08-29","npm":0,"name":"dsh-model-manager","owner":"Ansonfishing","short":"dsh-model-manager","slug":"Ansonfishing/dsh-model-manager","desc":"Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.","cmd":"dsh plugin --profile web add github:Ansonfishing/dsh-model-manager","href":"/p/Ansonfishing/dsh-model-manager/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-13","npm":0,"name":"reasoning-setup","owner":"Ayelsh","short":"reasoning-setup","slug":"Ayelsh/reasoning-setup","desc":"Edit reasoning effort levels and thinking formats for models that declare none.","cmd":"dsh plugin --profile web add \"https://github.com/Ayelsh/reasoning-setup/releases/latest/download/dsh-reasoning-setup.tgz\"","href":"/p/Ayelsh/reasoning-setup/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-23","npm":0,"name":"dsh-send-photos","owner":"Ayowait","short":"dsh-send-photos","slug":"Ayowait/dsh-send-photos","desc":"Declares image input on relay routes whose endpoint omits modality metadata, so models that can see photos stop being rejected as text-only. This also overrides routes that are explicitly declared text-only.","cmd":"dsh plugin --profile web add github:Ayowait/dsh-send-photos","href":"/p/Ayowait/dsh-send-photos/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-13","npm":0,"name":"deepseek-harness-plugin","owner":"Cci-65","short":"deepseek-harness-plugin","slug":"Cci-65/deepseek-harness-plugin","desc":"Adds configurable reasoning levels for third-party models and a model-strength picker in the composer.","cmd":"dsh plugin --profile web add github:Cci-65/deepseek-harness-plugin","href":"/p/Cci-65/deepseek-harness-plugin/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-25","npm":0,"name":"dsh-plugins#api-switcher","owner":"ccl4-56-23-5","short":"DSH-Plugins#api-switcher","slug":"ccl4-56-23-5/DSH-Plugins--Api-Switcher插件-2.3.0","desc":"Manage API providers and enabled models, with provider-grouped model switching and keyword search in the native model menu.","cmd":"dsh plugin --profile web add \"https://github.com/ccl4-56-23-5/DSH-Plugins/releases/download/api-switcher-v2.3.0/dsh-api-switcher-2.3.0.tgz\"","href":"/p/ccl4-56-23-5/DSH-Plugins--Api-Switcher插件-2.3.0/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-07","npm":0,"name":"dsh-model-modality","owner":"ct-jyjntc","short":"dsh-model-modality","slug":"ct-jyjntc/dsh-model-modality","desc":"Declare whether a configured third-party model accepts image (multimodal) input; writes the modality into the owning provider settings and verifies it through runtime model resolution.","cmd":"dsh plugin --profile web add github:ct-jyjntc/dsh-model-modality","href":"/p/ct-jyjntc/dsh-model-modality/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-16","npm":0,"name":"dsh-ofm-model-manager","owner":"DeepseekDays","short":"dsh-ofm-model-manager","slug":"DeepseekDays/dsh-ofm-model-manager","desc":"Per-model enable/disable and renaming for every provider in DeepSeek Harness: a panel at the bottom of Settings - Models with a search box, status chips with counts, a provider filter, collapsible provider groups with group-level switches, and batch actions scoped to the current view. Disabled models leave the model picker and custom names replace the built-in ones. Preferences persist in the profile and apply immediately, without reloading the page or restarting DSH.","cmd":"dsh plugin --profile web add github:DeepseekDays/dsh-ofm-model-manager","href":"/p/DeepseekDays/dsh-ofm-model-manager/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-16","npm":0,"name":"dsh-provider-toggle","owner":"DeepseekDays","short":"dsh-provider-toggle","slug":"DeepseekDays/dsh-provider-toggle","desc":"Adds a one-click switch to every provider row in Settings - Models: turn a provider off and it leaves the model picker, turn it back on and it returns. It works by wrapping the model catalog call, so it affects the catalog and the picker only, never routing, keys or provider config; existing sessions that already use such a model keep working.","cmd":"dsh plugin --profile web add github:DeepseekDays/dsh-provider-toggle","href":"/p/DeepseekDays/dsh-provider-toggle/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-18","npm":0,"name":"dsh-llm-config","owner":"EmotionG","short":"dsh-llm-config","slug":"EmotionG/dsh-llm-config","desc":"Requires DSH >= 0.2.0-rc.2 < 0.3.0. Declare any number of LLM providers, each with its own endpoint, credential and per-model parameters (reasoning-effort vocabulary, image input, retry policy), across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats, configured from a settings page.","cmd":"dsh plugin --profile web add \"https://github.com/EmotionG/dsh-llm-config/releases/download/v0.2.0/dsh-llm-config-0.2.0.tgz\"","href":"/p/EmotionG/dsh-llm-config/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-23","npm":1,"name":"dsh-ai-providers#cohere","owner":"Firefox2100","short":"dsh-ai-providers#cohere","slug":"Firefox2100/dsh-ai-providers--packages-dsh-ai-cohere","desc":"Cohere provider for language models, embeddings, and reranking through Cohere's native APIs in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.","cmd":"dsh plugin --profile web add @dsh-ai-providers/cohere","href":"/p/Firefox2100/dsh-ai-providers--packages-dsh-ai-cohere/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-24","npm":1,"name":"dsh-ai-providers#dashscope","owner":"Firefox2100","short":"dsh-ai-providers#dashscope","slug":"Firefox2100/dsh-ai-providers--packages-dsh-ai-dashscope","desc":"Alibaba Cloud DashScope provider for Qwen language models, embeddings, reranking, speech, and image generation through native APIs in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.","cmd":"dsh plugin --profile web add @dsh-ai-providers/dashscope","href":"/p/Firefox2100/dsh-ai-providers--packages-dsh-ai-dashscope/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-23","npm":1,"name":"dsh-ai-providers#jina","owner":"Firefox2100","short":"dsh-ai-providers#jina","slug":"Firefox2100/dsh-ai-providers--packages-dsh-ai-jina","desc":"Jina provider for embeddings and reranking in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.","cmd":"dsh plugin --profile web add @dsh-ai-providers/jina","href":"/p/Firefox2100/dsh-ai-providers--packages-dsh-ai-jina/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-24","npm":1,"name":"dsh-ai-providers#ollama","owner":"Firefox2100","short":"dsh-ai-providers#ollama","slug":"Firefox2100/dsh-ai-providers--packages-dsh-ai-ollama","desc":"Ollama provider for language models and embeddings, with model discovery, loading, and unloading in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.","cmd":"dsh plugin --profile web add @dsh-ai-providers/ollama","href":"/p/Firefox2100/dsh-ai-providers--packages-dsh-ai-ollama/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-24","npm":1,"name":"dsh-ai-providers#typesafe","owner":"Firefox2100","short":"dsh-ai-providers#typesafe","slug":"Firefox2100/dsh-ai-providers--packages-dsh-ai-typesafe","desc":"TypeSafe AI Jev decision provider for typed probabilistic choices and scores in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.","cmd":"dsh plugin --profile web add @dsh-ai-providers/typesafe","href":"/p/Firefox2100/dsh-ai-providers--packages-dsh-ai-typesafe/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-17","npm":0,"name":"deepseek-harness-trae","owner":"Fleey","short":"deepseek-harness-trae","slug":"Fleey/deepseek-harness-trae","desc":"Connects Trae enterprise models to DeepSeek Harness from a personal access token alone, calling llm_raw_chat directly with no trae2api or traecli process; fetches the model catalog from upstream on startup and shows remaining quota for personal packs and enterprise seats.","cmd":"dsh plugin --profile web add github:Fleey/deepseek-harness-trae","href":"/p/Fleey/deepseek-harness-trae/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-21","npm":0,"name":"dsh-baipiao-shigege","owner":"fortran2005","short":"dsh-baipiao-shigege","slug":"fortran2005/dsh-baipiao-shigege","desc":"Tiers free-channel models into three 1M fallback chains plus a custom chain; orders them by measured throughput, drops models below throughput or error-rate thresholds, and rotates accounts. Requires an OpenAI-compatible gateway (default :8326).","cmd":"dsh plugin --profile web add github:fortran2005/dsh-baipiao-shigege","href":"/p/fortran2005/dsh-baipiao-shigege/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-15","npm":0,"name":"dsh-dario-sidecar","owner":"GrannyProgramming","short":"dsh-dario-sidecar","slug":"GrannyProgramming/dsh-dario-sidecar","desc":"Harness-owned lifecycle for the dario proxy — starts it with your harness, readiness-gates it, and stops it when the harness stops, so subscription-backed (Claude/ChatGPT) model routes just work.","cmd":"dsh plugin --profile web add github:GrannyProgramming/dsh-dario-sidecar","href":"/p/GrannyProgramming/dsh-dario-sidecar/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-17","npm":0,"name":"dsh-connect-cursor","owner":"greatyao","short":"dsh-connect-cursor","slug":"greatyao/dsh-connect-cursor","desc":"Connects a locally-signed-in Cursor desktop app to dsh as a native LlmAdapter — reads the Cursor login token from state.vscdb or auth.json, drives the private agent.v1.AgentService/Run HTTP/2 bidi stream, and translates InteractionUpdate deltas into dsh StreamChunks. No loopback proxy. macOS, Windows and Linux.","cmd":"dsh plugin --profile web add github:greatyao/dsh-connect-cursor","href":"/p/greatyao/dsh-connect-cursor/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-17","npm":0,"name":"dsh-llm-moe4all","owner":"Headmaster218","short":"dsh-llm-moe4all","slug":"Headmaster218/dsh-llm-moe4all","desc":"Runs MoE4All models locally in DSH with automatic engine installation, model discovery and downloads, inference settings, and live speed monitoring, or connects to an existing service.","cmd":"dsh plugin --profile web add \"https://github.com/Headmaster218/dsh-llm-moe4all/releases/latest/download/dsh-llm-moe4all.tgz\"","href":"/p/Headmaster218/dsh-llm-moe4all/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-18","npm":0,"name":"dsh-standardcompute","owner":"henrikdukefoss","short":"dsh-standardcompute","slug":"henrikdukefoss/dsh-standardcompute","desc":"Adds Standard Compute as an OpenAI-compatible model provider through the built-in pi-ai adapter, with its standardcompute router model and two direct model pins; configuration only, no code.","cmd":"dsh plugin --profile web add \"https://github.com/henrikdukefoss/dsh-standardcompute/releases/latest/download/dsh-standardcompute.tgz\"","href":"/p/henrikdukefoss/dsh-standardcompute/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-15","npm":0,"name":"dsh-model-modality","owner":"hmtxj","short":"dsh-model-modality","slug":"hmtxj/dsh-model-modality","desc":"Per-model input type and thinking level declarations on the 模型 settings page — 输入类型 checkboxes on every provider card, and a 思考等级 field in the provider 编辑 dialog. Writes the official pi-ai input and reasoningEfforts fields.","cmd":"dsh plugin --profile web add github:hmtxj/dsh-model-modality","href":"/p/hmtxj/dsh-model-modality/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-21","npm":0,"name":"dsh-llm-cc-switch","owner":"Hoemr","short":"dsh-llm-cc-switch","slug":"Hoemr/dsh-llm-cc-switch","desc":"Exposes the accounts in a local CC Switch database to DeepSeek Harness: every account (Claude Code, Codex, OpenCode, Grok Build) becomes a model category in the picker, and the SQLite database is re-read on every model listing and request, so switching accounts in CC Switch needs no DSH restart. Requires CC Switch and the DSH desktop app.","cmd":"dsh plugin --profile web add github:Hoemr/dsh-llm-cc-switch","href":"/p/Hoemr/dsh-llm-cc-switch/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-24","npm":1,"name":"dsh-connect-scnet","owner":"hualuo520-h","short":"dsh-connect-scnet","slug":"hualuo520-h/dsh-connect-scnet","desc":"Brings the models of the SCNet (超算互联网) Computing Service desktop client into DSH by reusing the API key that client already wrote, with a 30-model catalog and a per-model default thinking level.","cmd":"dsh plugin --profile web add dsh-connect-scnet","href":"/p/hualuo520-h/dsh-connect-scnet/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-21","npm":0,"name":"dsh-native-provider","owner":"libre-webui","short":"dsh-native-provider","slug":"libre-webui/dsh-native-provider","desc":"Use your DSH models in [Libre WebUI](https://github.com/libre-webui/libre-webui) for chat, sandboxed Work and usage tracking, with provider credentials kept in DSH. Requires Libre WebUI 0.37.0 or later.","cmd":"dsh plugin --profile web add github:libre-webui/dsh-native-provider","href":"/p/libre-webui/dsh-native-provider/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-20","npm":0,"name":"dsh-framework-doctor","owner":"lj100886","short":"dsh-framework-doctor","slug":"lj100886/dsh-framework-doctor","desc":"Configure model providers by probing their endpoint, check DeepSeek Harness health, and repair what can be fixed.","cmd":"dsh plugin --profile web add github:lj100886/dsh-framework-doctor","href":"/p/lj100886/dsh-framework-doctor/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-17","npm":0,"name":"dsh-model-config","owner":"lsdt45","short":"dsh-model-config","slug":"lsdt45/dsh-model-config","desc":"Configure thinking toggles and reasoning efforts per model for llm-pi-ai and official DeepSeek, and specify input modalities (input or inputModalities) in the DSH settings panel.","cmd":"dsh plugin --profile web add github:lsdt45/dsh-model-config","href":"/p/lsdt45/dsh-model-config/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-16","npm":0,"name":"dsh-qoder-connect","owner":"marsma-101","short":"dsh-qoder-connect","slug":"marsma-101/dsh-qoder-connect","desc":"Connects Qoder CN desktop app models to DeepSeek Harness with zero user interaction: decrypts local OSCrypt credentials, signs requests with the COSY scheme against the CN gateway, and lists 14 models with free-tier badges.","cmd":"dsh plugin --profile web add github:marsma-101/dsh-qoder-connect","href":"/p/marsma-101/dsh-qoder-connect/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-16","npm":0,"name":"dsh-trae-connect","owner":"marsma-101","short":"dsh-trae-connect","slug":"marsma-101/dsh-trae-connect","desc":"Connects Trae CN desktop app models to DeepSeek Harness with no OAuth flow: reuses the desktop sign-in, exposes 17 models (including deepseek-v4.1-flash) with consumption-rate badges and reasoning-effort mapping.","cmd":"dsh plugin --profile web add github:marsma-101/dsh-trae-connect","href":"/p/marsma-101/dsh-trae-connect/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-23","npm":0,"name":"dsh-codex-plus","owner":"mia-wong1016","short":"dsh-codex-plus","slug":"mia-wong1016/dsh-codex-plus","desc":"Brings the Codex (ChatGPT Plus/Pro) subscription already signed in on this machine into DSH. It (1) shows the 5-hour and weekly windows with their reset times and the remaining reset credits in a sidebar panel, with one-click reset that consumes a credit; (2) registers the subscription route in llm-pi-ai (openai-codex) when the quota is read, so the Codex models appear in the model picker; (3) refreshes the OAuth access token before expiry and writes it back atomically, so no key has to be replaced by hand; and (4) adds a codex tool that delegates a task to the local Codex agent. No API key has to be entered.","cmd":"dsh plugin --profile web add \"https://github.com/mia-wong1016/dsh-codex-plus/releases/download/v0.1.4/dsh-codex-plus-0.1.4.tgz\"","href":"/p/mia-wong1016/dsh-codex-plus/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-16","npm":0,"name":"missher-dsh-reasoning-effort","owner":"Missher12","short":"Missher-DSH-Reasoning-Effort","slug":"Missher12/Missher-DSH-Reasoning-Effort","desc":"Adds a thinking-depth slider mapped to declared model levels, configuration guidance, and optional inline model settings.","cmd":"dsh plugin --profile web add \"https://github.com/Missher12/Missher-DSH-Reasoning-Effort/releases/download/v0.7.5-local.15/missher-dsh-reasoning-effort-0.7.5-local.15.tgz\"","href":"/p/Missher12/Missher-DSH-Reasoning-Effort/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-16","npm":0,"name":"dsh-xiaoyiwork-connect","owner":"moxiaoren","short":"dsh-xiaoyiwork-connect","slug":"moxiaoren/dsh-xiaoyiwork-connect","desc":"Reuses the local model proxy of a logged-in XiaoyiWork desktop app (Windows only) so its models appear in DeepSeek Harness without a separate API key.","cmd":"dsh plugin --profile web add github:moxiaoren/dsh-xiaoyiwork-connect","href":"/p/moxiaoren/dsh-xiaoyiwork-connect/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-08-13","npm":0,"name":"qwen-mm-plugins","owner":"omdsh-dev","short":"Qwen-MM-Plugins","slug":"omdsh-dev/Qwen-MM-Plugins","desc":"Qwen multi-modal plugin support.","cmd":"dsh plugin --profile web add github:omdsh-dev/Qwen-MM-Plugins","href":"/p/omdsh-dev/Qwen-MM-Plugins/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-11","npm":0,"name":"dsh-ollama","owner":"orzgithub","short":"dsh-ollama","slug":"orzgithub/dsh-ollama","desc":"Use local Ollama in DSH with Ollama native API and params support.","cmd":"dsh plugin --profile web add github:orzgithub/dsh-ollama","href":"/p/orzgithub/dsh-ollama/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-24","npm":0,"name":"dsh-openai-gateway","owner":"pigman18","short":"dsh-openai-gateway","slug":"pigman18/dsh-openai-gateway","desc":"Exposes every model of every provider configured in DeepSeek Harness through one OpenAI-compatible endpoint on a fixed loopback port, with a sidebar page for the base URL, key, port and model ids.","cmd":"dsh plugin --profile web add github:pigman18/dsh-openai-gateway","href":"/p/pigman18/dsh-openai-gateway/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-18","npm":0,"name":"dsh-openai-oauth","owner":"pyh-pan","short":"dsh-openai-oauth","slug":"pyh-pan/dsh-openai-oauth","desc":"Use ChatGPT subscriptions in DeepSeek Harness Desktop via official Sign in with ChatGPT, with dynamic Agent registration and native model and reasoning selection.","cmd":"dsh plugin --profile web add github:pyh-pan/dsh-openai-oauth","href":"/p/pyh-pan/dsh-openai-oauth/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-20","npm":0,"name":"dsh-cc-switch-bridge","owner":"qipengxiang","short":"dsh-cc-switch-bridge","slug":"qipengxiang/dsh-cc-switch-bridge","desc":"Bridges the third-party providers saved in a local cc-switch app into DeepSeek Harness: Anthropic-format tool groups become adapter routes, Codex groups are handed to the built-in pi-ai adapter, and a settings page picks which groups to import and in which order.","cmd":"dsh plugin --profile web add github:qipengxiang/dsh-cc-switch-bridge","href":"/p/qipengxiang/dsh-cc-switch-bridge/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-08-27","npm":0,"name":"changmodel","owner":"qq928820655","short":"changmodel","slug":"qq928820655/changmodel","desc":"Model switching, model capability configuration, fixed compaction models, subagent routing, and input history enhancement.","cmd":"dsh plugin --profile web add github:qq928820655/changmodel","href":"/p/qq928820655/changmodel/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-17","npm":0,"name":"dsh-better-reasoning","owner":"Rczlin","short":"dsh-better-reasoning","slug":"Rczlin/dsh-better-reasoning","desc":"Gives pi-ai routed models a reasoning-effort ladder without manual settings: falls back declared to models.dev to a 7-tier default, and replaces the composer model chip with a Codex-style vertical picker.","cmd":"dsh plugin --profile web add github:Rczlin/dsh-better-reasoning","href":"/p/Rczlin/dsh-better-reasoning/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-08-30","npm":0,"name":"dsh-llm-mlx","owner":"robbywang25","short":"dsh-llm-mlx","slug":"robbywang25/dsh-llm-mlx","desc":"Use local MLX-LM or MLX-VLM models in DeepSeek Harness through a loopback OpenAI-compatible provider, with optional DSH-owned server startup.","cmd":"dsh plugin --profile web add \"https://github.com/robbywang25/dsh-llm-mlx/releases/download/v0.4.0/dsh-llm-mlx-0.4.0.tgz\"","href":"/p/robbywang25/dsh-llm-mlx/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-06","npm":0,"name":"dsh-model-groups","owner":"roclee2692","short":"dsh-model-groups","slug":"roclee2692/dsh-model-groups","desc":"Grouped provider and manufacturer model selector for DeepSeek Harness, preserving provider/model routes and reasoning levels.","cmd":"dsh plugin --profile web add github:roclee2692/dsh-model-groups","href":"/p/roclee2692/dsh-model-groups/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-17","npm":0,"name":"dsh-model-smart-config","owner":"Seller-1990","short":"dsh-model-smart-config","slug":"Seller-1990/dsh-model-smart-config","desc":"Recognizes a model ID in the DeepSeek Harness model catalog and fills that row's context window, input modalities and reasoning levels as editable suggestions, from a bundled offline rule table covering 33 vendors.","cmd":"dsh plugin --profile web add \"https://github.com/Seller-1990/dsh-model-smart-config/releases/download/v0.3.3/dsh-model-smart-config-0.3.3.tgz\"","href":"/p/Seller-1990/dsh-model-smart-config/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-17","npm":0,"name":"dsh-zen-adapter","owner":"seonzzy","short":"dsh-zen-adapter","slug":"seonzzy/dsh-zen-adapter","desc":"Registers OpenCode Zen free models as a native provider: the catalog is discovered live from opencode.ai intersected with models.dev pricing, and a detail page can re-fetch it or test which models answer. Declares no dependencies, so the host's pi-ai stays the only one.","cmd":"dsh plugin --profile web add github:seonzzy/dsh-zen-adapter","href":"/p/seonzzy/dsh-zen-adapter/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-24","npm":0,"name":"dsh-aimy","owner":"Sheep1x","short":"dsh-aimy","slug":"Sheep1x/dsh-aimy","desc":"Manages a relay station's many groups and rates for DSH, switching the station's billing group in place and refreshing the model list and rate on stations that expose /v1/token/group; stations without it fall back to read-only and keep serving models.","cmd":"dsh plugin --profile web add github:Sheep1x/dsh-aimy","href":"/p/Sheep1x/dsh-aimy/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-20","npm":0,"name":"dsh-credit-hub","owner":"spdw666","short":"dsh-credit-hub","slug":"spdw666/dsh-credit-hub","desc":"Native multi-platform accounts and model routing with staggered check-ins, event notifications, and quota forecasts. Its background worker needs a standalone Node >=22.23.3 with node:sqlite (enforced by engines.node); Qwen Office coding additionally needs Python with cryptography and wasmtime.","cmd":"dsh plugin --profile web add \"https://github.com/spdw666/dsh-credit-hub/releases/latest/download/dsh-credit-hub.tgz\"","href":"/p/spdw666/dsh-credit-hub/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-19","npm":0,"name":"coding-plan","owner":"STLI69","short":"coding-plan","slug":"STLI69/coding-plan","desc":"Volcengine Ark Coding Plan provider route for DeepSeek Harness with all 15 Coding Plan models and per-model reasoning-effort control, generated from a single source and drift-checked weekly.","cmd":"dsh plugin --profile web add github:STLI69/coding-plan","href":"/p/STLI69/coding-plan/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-23","npm":0,"name":"dsh-llm-chatgpt-web","owner":"sunyifeisb-art","short":"dsh-llm-chatgpt-web","slug":"sunyifeisb-art/dsh-llm-chatgpt-web","desc":"Answers model calls by driving your own logged-in chatgpt.com session in a local Chrome, so inference spends the ChatGPT web quota rather than Codex quota, and adds a JSON tool-call protocol so the web model can run DSH tools.","cmd":"dsh plugin --profile web add github:sunyifeisb-art/dsh-llm-chatgpt-web","href":"/p/sunyifeisb-art/dsh-llm-chatgpt-web/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-16","npm":0,"name":"dsh-apply-model-all","owner":"SYXliuliuliu","short":"dsh-apply-model-all","slug":"SYXliuliuliu/dsh-apply-model-all","desc":"Apply the current session's model to every other session in one click, from a control beside the composer's model picker.","cmd":"dsh plugin --profile web add github:SYXliuliuliu/dsh-apply-model-all","href":"/p/SYXliuliuliu/dsh-apply-model-all/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-23","npm":0,"name":"dsh-codex-native","owner":"Tests4gptplay","short":"dsh-codex-native","slug":"Tests4gptplay/dsh-codex-native","desc":"Uses OpenAI GPT via the official Codex app-server, with ChatGPT subscription login, DSH tools, native settings, quota and manual token usage history.","cmd":"dsh plugin --profile web add \"https://github.com/Tests4gptplay/dsh-codex-native/releases/download/v0.2.1-alpha.5/dsh-codex-native-0.2.1-alpha.5.tgz\"","href":"/p/Tests4gptplay/dsh-codex-native/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-16","npm":0,"name":"dsh-model-control","owner":"uio-o","short":"dsh-model-control","slug":"uio-o/dsh-model-control","desc":"Replaces the composer model seat with a search-first picker and adds a model management page: create and edit llm-pi-ai channels, choose which of an endpoint's models exist, and declare per-model thinking ladders and capabilities.","cmd":"dsh plugin --profile web add github:uio-o/dsh-model-control","href":"/p/uio-o/dsh-model-control/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-23","npm":0,"name":"dsh-opencodego","owner":"whoiszzj","short":"dsh-opencodego","slug":"whoiszzj/dsh-opencodego","desc":"OpenCode Go provider that verifies a model against the gateway rather than treating a recommendation as a measurement: the models.dev protocol suggestion is probed before it is used, reasoning levels follow a measured contract, and requests run through an ordered protocol fallback chain. Context window, max output and image-input numbers are declared by a runtime-refreshed models.dev layer rather than probed, with operator overrides above both. Several OpenCode Go credentials can be stored and switched from the settings page.","cmd":"dsh plugin --profile web add github:whoiszzj/dsh-opencodego","href":"/p/whoiszzj/dsh-opencodego/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-20","npm":0,"name":"dsh-connect-qoder-pro","owner":"wshdp123","short":"dsh-connect-qoder-pro","slug":"wshdp123/dsh-connect-qoder-pro","desc":"Connects DSH to the local Qoder desktop client's sign-in to expose Qoder CN models (qmodel, qfmodel). Windows only: the credential is decrypted with DPAPI.","cmd":"dsh plugin --profile web add github:wshdp123/dsh-connect-qoder-pro","href":"/p/wshdp123/dsh-connect-qoder-pro/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-17","npm":0,"name":"dsh-aux-degrade","owner":"xiamubumu","short":"dsh-aux-degrade","slug":"xiamubumu/dsh-aux-degrade","desc":"Stops compaction summaries and session titles from burning their output budget on reasoning, by lowering the thinking level and raising the token floor for auxiliary calls only.","cmd":"dsh plugin --profile web add \"https://github.com/xiamubumu/dsh-aux-degrade/releases/download/v1.1.0/dsh-aux-degrade-1.1.0.tgz\"","href":"/p/xiamubumu/dsh-aux-degrade/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-19","npm":0,"name":"dsh-freemodels-opencode","owner":"xiean676","short":"dsh-freemodels-opencode","slug":"xiean676/dsh-freemodels-opencode","desc":"Connects the OpenCode Zen anonymous free lane to DeepSeek Harness: refresh the model list from upstream, tick which models the opencode provider exposes, test any of them with a real request that ends in one of seven verdicts, and order both the settings card and the model selector by a hand-written S/A/B/C capability rating.","cmd":"dsh plugin --profile web add github:xiean676/dsh-freemodels-opencode","href":"/p/xiean676/dsh-freemodels-opencode/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-20","npm":0,"name":"dsh-connect-minimax","owner":"Yuedalao","short":"dsh-connect-minimax","slug":"Yuedalao/dsh-connect-minimax","desc":"Connects an existing local MiniMax Code sign-in to DeepSeek Harness through a loopback reverse proxy without storing an API key or signing out.","cmd":"dsh plugin --profile web add \"https://github.com/Yuedalao/dsh-connect-minimax/releases/latest/download/dsh-connect-minimax.tgz\"","href":"/p/Yuedalao/dsh-connect-minimax/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-17","npm":0,"name":"dmxapi-dsh","owner":"YV919","short":"dmxapi-dsh","slug":"YV919/dmxapi-dsh","desc":"Configure DMXAPI Chat Completions, Responses, Anthropic Messages, and custom providers; edit models on existing preset routes.","cmd":"dsh plugin --profile web add \"https://github.com/YV919/dmxapi-dsh/releases/download/v0.2.2/dsh-dmxapi-0.2.2.tgz\"","href":"/p/YV919/dmxapi-dsh/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-10-24","npm":1,"name":"dsh-newapi-provider","owner":"zenVibeCoding","short":"dsh-newapi-provider","slug":"zenVibeCoding/dsh-newapi-provider","desc":"New API gateway provider: several gateways with one active at a time, per-gateway model lists with context and modality details, quota, and image and video generation tools.","cmd":"dsh plugin --profile web add dsh-newapi-provider","href":"/p/zenVibeCoding/dsh-newapi-provider/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-07","npm":0,"name":"dsh-zhipu-toolkit","owner":"Zn-Dk","short":"dsh-zhipu-toolkit","slug":"Zn-Dk/dsh-zhipu-toolkit","desc":"Dual-endpoint Zhipu BigModel GLM provider catalog (Coding Plan and ordinary API) with live model discovery, live-tested thinking-tier mapping, and a settings card for keys, endpoints and the default reasoning tier.","cmd":"dsh plugin --profile web add github:Zn-Dk/dsh-zhipu-toolkit","href":"/p/Zn-Dk/dsh-zhipu-toolkit/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-13","npm":0,"name":"dsh-context-budget","owner":"zpis666","short":"dsh-context-budget","slug":"zpis666/dsh-context-budget","desc":"Adds per-route context window and compaction threshold fields to the Models settings page and a vendor-aware thinking-effort picker to the composer, writing llm-pi-ai capacities, reasoningEfforts, and a compaction-basic patch row.","cmd":"dsh plugin --profile web add github:zpis666/dsh-context-budget","href":"/p/zpis666/dsh-context-budget/"},{"cat":"model","tag":"Models & Providers","dl":null,"stars":0,"added":"2026-09-24","npm":0,"name":"dsh-provider-switch","owner":"zuojinxin","short":"dsh-provider-switch","slug":"zuojinxin/dsh-provider-switch","desc":"Enable or disable model providers, search models in the selector, and rename provider display names.","cmd":"dsh plugin --profile web add github:zuojinxin/dsh-provider-switch","href":"/p/zuojinxin/dsh-provider-switch/"}]}