{"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":"agi","tag":"AGI Architecture Exploration","dl":63975,"stars":16,"added":"2026-09-18","npm":1,"name":"dsh-pua","owner":"MichengAI","short":"dsh-pua","slug":"MichengAI/dsh-pua","desc":"Adds /pua to steer the agent to try another approach and verify results before claiming completion, with 15 company styles, persona modes, global and per-conversation settings, and an optional loop that continues until a verification command passes, the iteration limit is reached, or the user cancels.","cmd":"dsh plugin --profile web add @michengai/dsh-pua","href":"/p/MichengAI/dsh-pua/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":28596,"stars":365,"added":"2026-08-14","npm":1,"name":"dsh-memory","owner":"FuRongJun-1999","short":"dsh-memory","slug":"FuRongJun-1999/dsh-memory","desc":"White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.","cmd":"dsh plugin --profile web add @furongjun1999/dsh-memory","href":"/p/FuRongJun-1999/dsh-memory/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":6641,"stars":17,"added":"2026-09-01","npm":1,"name":"dsh-engram","owner":"kenz1117","short":"dsh-engram","slug":"kenz1117/dsh-engram","desc":"Cross-session long-term memory under the \"memory palace\" metaphor: dual-scope SQLite stores (user + per-git-origin project), hybrid FTS5 + local-vector retrieval with RRF fusion and recency/proof ranking boost, automatic capture from the session log (including the final turn), provenance audit chains, consolidation distillation and decay forgetting, and a settings-page Memory Library panel with corridor topology, tour butler, and refurb list.","cmd":"dsh plugin --profile web add @kenz1117/dsh-engram","href":"/p/kenz1117/dsh-engram/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":5371,"stars":0,"added":"2026-09-24","npm":1,"name":"muche-dsh-plugin","owner":"NEINC1","short":"muche-dsh-plugin","slug":"NEINC1/muche-dsh-plugin","desc":"Chat panel for the MuChe companion with per-user backend settings, plus an outbound bridge that runs tasks on the user's local dsh.","cmd":"dsh plugin --profile web add muche-dsh-plugin","href":"/p/NEINC1/muche-dsh-plugin/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":4405,"stars":3,"added":"2026-09-23","npm":1,"name":"dsh-linghun","owner":"syyr1987","short":"dsh-linghun","slug":"syyr1987/dsh-linghun","desc":"A judgment core for DeepSeek Harness: a cognition loop that gives every decision a source and attribution and drives planning to a close, hippocampus memory that condenses running experience into reusable knowledge, and a customizable persona card (name, personality, communication style). Requires DSH ^0.1.0-rc.7.","cmd":"dsh plugin --profile web add dsh-linghun","href":"/p/syyr1987/dsh-linghun/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":4001,"stars":1335,"added":"2026-10-08","npm":1,"name":"clearai-dsh","owner":"Clearailhc","short":"clearai-dsh","slug":"Clearailhc/clearai-dsh","desc":"An agent preset for evidence-checked research: every step advances only through system-verified observations, L3+ claims go to an independent evaluator, and the session folds into a replayable ledger that grows into a browsable domain ontology. Requires DSH >=0.1.7-alpha.1.","cmd":"dsh plugin --profile web add clearai-dsh","href":"/p/Clearailhc/clearai-dsh/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":3510,"stars":11,"added":"2026-09-18","npm":1,"name":"dsh-heartbeat","owner":"Kanadego","short":"dsh-heartbeat","slug":"Kanadego/dsh-heartbeat","desc":"Heartbeat loop for DeepSeek Harness: every 20 minutes (by default) the agent wakes on its own to keep a local profile of your interests and preferences, search the web for things you care about, and keep what it finds. When it has something worth sharing, it sends a short package of notes to the sessions you link it to. A set of rules in code - quiet hours, busy windows, a daily limit, a cooldown - decides whether it may speak at all, and the agent in that session decides whether to actually say anything. Windows only.","cmd":"dsh plugin --profile web add @kanadego/dsh-heartbeat","href":"/p/Kanadego/dsh-heartbeat/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":2495,"stars":4,"added":"2026-09-09","npm":1,"name":"dsh-answer-reviewer","owner":"bycall","short":"dsh-answer-reviewer","slug":"bycall/dsh-answer-reviewer","desc":"Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config from the Reviewer 配置 tab in the conversation view ring above the composer (对话 / 轨迹 / 记忆系统 / Reviewer 配置), from a 127.0.0.1 HTTP server, or from an optional right-sidebar tab via dsh-better-sidebar.","cmd":"dsh plugin --profile web add dsh-answer-reviewer","href":"/p/bycall/dsh-answer-reviewer/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":2279,"stars":2,"added":"2026-09-21","npm":1,"name":"dsh-proactive","owner":"john-walks-slow","short":"dsh-proactive","slug":"john-walks-slow/dsh-proactive--packages-dsh-proactive","desc":"Host-level proactive wake-ups for DeepSeek Harness: the model schedules its own alarms (once, recurring interval, or cron, with optional random jitter), cold sessions are woken on time by session resume, model-initiated follow-ups are gated by quiet hours and a daily delivery budget, silent wake turns end with proactive_reclaim and fold out of model context as tombstones, declared schedule files glob-sync JSON schedules into host alarms idempotently, min_idle_seconds defers wakes until the destination session quiets down, and a web panel (settings section plus per-session tab, SSE live refresh) manages alarms and wake history — the heartbeat engine for AI companions and roleplay characters with their own daily routines and world evolution.","cmd":"dsh plugin --profile web add dsh-proactive","href":"/p/john-walks-slow/dsh-proactive--packages-dsh-proactive/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":1934,"stars":3,"added":"2026-09-19","npm":1,"name":"dsh-advisor-plugin","owner":"leeyoung1","short":"dsh-advisor-plugin","slug":"leeyoung1/dsh-advisor-plugin","desc":"Pairs the running executor with a stronger reviewer model through zero-parameter advisor() calls and step-based patrol checks, returning plan, correction, or stop guidance.","cmd":"dsh plugin --profile web add dsh-advisor-plugin","href":"/p/leeyoung1/dsh-advisor-plugin/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":1876,"stars":3,"added":"2026-09-20","npm":1,"name":"orbital-agents","owner":"Qulierm","short":"orbital-agents","slug":"Qulierm/orbital-agents","desc":"Persistent Endeavour and Challenger peer sessions for DeepSeek Harness that plan, execute sequential tasks, and verify reported results.","cmd":"dsh plugin --profile web add dsh-orbital-agents","href":"/p/Qulierm/orbital-agents/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":1837,"stars":4,"added":"2026-09-20","npm":1,"name":"dsh-j-space","owner":"AnonyJcy","short":"dsh-j-space","slug":"AnonyJcy/dsh-j-space","desc":"J-Space Cognition Suite SV1 native agent preset and standalone Cordis plugin: 13 modules, persistent controller and decoupled workspace.","cmd":"dsh plugin --profile web add @anonyjcy/dsh-j-space","href":"/p/AnonyJcy/dsh-j-space/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":1497,"stars":2,"added":"2026-09-21","npm":1,"name":"dsh-simulated-life","owner":"john-walks-slow","short":"dsh-simulated-life","slug":"john-walks-slow/dsh-simulated-life","desc":"Simulated life context for DeepSeek Harness: every turn injects the past 24h of simulated life events from the workspace .life/ directory (sliding-window filter, session-level deduplication with delta updates, world summary) as a collapsed context notice, and the life_react tool lets the agent record feelings, thoughts and actions back into its life log for the next round of world evolution — turning a DSH agent into a roleplay character with a persistent daily life.","cmd":"dsh plugin --profile web add dsh-simulated-life","href":"/p/john-walks-slow/dsh-simulated-life/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":1291,"stars":2,"added":"2026-09-11","npm":1,"name":"dsh-loop-continue","owner":"yunxiyang","short":"dsh-loop-continue","slug":"yunxiyang/dsh-loop-continue","desc":"Resumes an agent turn that ended after narrating its next action without calling a tool: the guard replays the turn log on agent/turn-stopping, asks a judge model one true/false question, and steers the same turn to run one more step.","cmd":"dsh plugin --profile web add dsh-loop-continue","href":"/p/yunxiyang/dsh-loop-continue/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":1284,"stars":6,"added":"2026-09-03","npm":1,"name":"dsh-gungnir#dsh-plugin","owner":"Jonah-Wu23","short":"dsh-gungnir#dsh-plugin","slug":"Jonah-Wu23/dsh-gungnir--packages-dsh-plugin","desc":"Evidence-driven goal verification plugin for DeepSeek Harness. Locks goals via /ultragoal and verifies completion against command exit codes and generated artifacts, preventing the model from falsely reporting task completion.","cmd":"dsh plugin --profile web add dsh-gungnir","href":"/p/Jonah-Wu23/dsh-gungnir--packages-dsh-plugin/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":null,"stars":3,"added":"2026-09-30","npm":0,"name":"portable-dsh-multi-agent-plugin","owner":"WDahah","short":"portable-dsh-multi-agent-plugin","slug":"WDahah/portable-dsh-multi-agent-plugin","desc":"Route each task to one model and its review to a different one, with qualification evidence, failover and a durable journal.","cmd":"dsh plugin --profile web add github:WDahah/portable-dsh-multi-agent-plugin","href":"/p/WDahah/portable-dsh-multi-agent-plugin/"},{"cat":"agi","tag":"AGI Architecture Exploration","dl":null,"stars":2,"added":"2026-09-06","npm":0,"name":"dsh-quality-review","owner":"CAI-MH","short":"dsh-quality-review","slug":"CAI-MH/dsh-quality-review","desc":"Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn and SOP-folder standards injected as an extra review dimension.","cmd":"dsh plugin --profile web add github:CAI-MH/dsh-quality-review","href":"/p/CAI-MH/dsh-quality-review/"}]}