Awesome DeepSeek Harness Plugin

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

Runs TiddlyWiki 5 as the DSH persistent knowledge base: ten tiddlywiki_* agent tools (filtered search, read/write/batch/rename/delete, recent, tags, git sync with conflict resolve), a full TiddlyWiki editor embedded in the GUI center column over a same-origin proxy, a right-side wiki tab, a per-session tab summarizing the notes a session read or wrote, a quick-note card with draft auto-save, and an optional clip bookmarklet with image attachment — all backed by an auto-committing git repository.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

Proactive associative memory for DSH: zero-prompt recall injected at a fixed boundary, three-layer auto-consolidation, skill crystallization, and Astra-style context management - handoff ledgers and a PLAN whiteboard that survive context-window switches, water-level sensing with an auto-detected model window. Local Markdown storage, model-agnostic, zero deps; lexical 0GB floor with optional semantic tiers.

A self-contained second brain for DeepSeek Harness — auto-captures durable dialogue knowledge into a local Markdown vault (custom dedup, CJK search, git-friendly), with a graphical knowledge base and an interactive knowledge graph (legend filter, time-dimension coloring, box-select, merge, delete, PNG export/import).

Recent conversations stay vivid. Older ones fade into summaries, not oblivion. StrataGate gives DeepSeek Harness six-layer, time-decaying memory, while lasting events and relationships settle into a knowledge graph. Bring your memories from other AIs with you—no need to start over.

Project-scoped cross-session memory: seven-layer SQLite store (soul/user/project/fact/lesson/rules/topic) on node:sqlite, cache-friendly first-message injection plus per-message keyword hits, memory_remember/search/find_similar/read/update/project tools, and idle-window consolidation ("dream") with peak-hour suppression. Prompt texts ship as per-language data files — the framework supports multilingual users.

Provides local and remote knowledge bases with project- and session-scoped recall, controlled write-back, and an embedded Web management console.

DSH bundle plugin that mounts 8 Project Memory skills, bootstraps memory architecture on first use, and registers codebase-memory bridge tools.

Bounded, layered, approval-gated, auditable cross-session memory: a typed `ctx.memory` seam with a zero-dependency SQLite provider, a `memory` tool, and frozen snapshot injection, plus the dsh-memory-protocol v1 rehearsal with an adapter registry and a distributable conformance suite.

Project memory for dsh with native task-system integration: session todos and file reads auto-condense into cross-session task records (task↔file links), so workflows are switchable and resumable without re-contextualizing. Read-time memory (no upfront scan): extracts code symbols, summarizes docs, and cross-links docs↔symbols; optional TS semantic enhancement (auto on when TS installed). Experience notes auto-dedup. Every recall includes a traceable citation. Pure JS, single dep, works out of the box, silent operation, zero overhead.

Workspace-isolated durable memory for DSH, with searchable, auditable, correctable, and removable workspace memories plus controlled global memory.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forget tools behind a human-confirm gate, and global + project-scoped JSON stores that follow your git repo.

Human-readable Markdown memory for DeepSeek Harness: user-level (~/.deepseek-harness/MEMORY.md) + workspace-level memory injected every turn, auto daily-log writing with distillation, bridges existing WorkBuddy/CodeBuddy memory dirs, memory_note / memory_note_user / memory_read tools with built-in dedup, and a bilingual settings page. Plain-text storage, no database.

Long-term memory for DSH: conversations auto-distilled into atomic facts, scene summaries and a persona profile, with relevant memories injected before every model step. Zero-config out of the box — hybrid BM25 + vector retrieval, optional offline local embeddings, chat/work family separation.

Manage soul.md persona cards and long-term memory, with workspace and session persona selection and tools to read and update them.

Reads the session files thirty-three other coding agents on this machine already wrote — Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more — including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).

Self-built DSH memory plugin: SQLite persistent storage + database-level audit guard (enforceAudit) + audit log. Auto-captures knowledge after conversations, agents recall via memory_recall, supports Claude Code/Codex/Cursor multi-agent sharing. Zero external dependencies.

Local-only project memory with zero bundled runtime dependencies or external services: JSON as the source of truth plus generated PROJECT_MEMORY.md, token-bounded session-frozen Hot Memory for prompt-prefix cache stability, cached cross-project BM25 recall, trusted session/turn provenance, explainable pre-write duplicate/conflict governance, editable importance/pin/tags/supersede/archive lifecycle, configurable top-level turn-end distillation, and a bilingual Web GUI for search, inspection, diagnostics, and live settings.

Self-tending living memory in one local SQLite file — a nightly patrol dedupes, merges, decays and cross-links entries on its own, with seven-signal RRF hybrid recall (FTS5 + jieba Chinese-first tokenization, optional vector KNN, graph PPR), a typed knowledge graph, conflict detection instead of silent overwrites, and web telemetry panels.

Local literature knowledge-base RAG: 10 tools (kb_ingest, kb_search, kb_rag, kb_zotero, kb_dedup, kb_clear, kb_fetch, kb_scope, kb_stats, kb_status), hybrid BM25+vector+reranker search, cited QA with clickable DOI links, all-local bge embeddings over a single-file SQLite index. Needs Python 3.9+ with pymupdf, faiss-cpu and sentence-transformers; the `npx dsh-kb-rag-install` installer sets those up and pre-downloads the model.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill.

Connects DeepSeek Harness to Busabase: search workspace knowledge, work with structured records and apps, submit writes as reviewable ChangeRequests, and inspect results in live cards.

TencentDB Agent Memory integration with conversation capture, structured memory extraction, automatic recall, and memory and conversation search tools.

Reversible context slimming for DeepSeek Harness: TOON-style lossless tabular re-encoding of uniform JSON arrays, stride-sampled table windows with line numbers, and cross-turn dedup for repeated tool output; every replacement passes a byte-plus-token gate (≤72% bytes, strictly fewer estimated tokens) and the original is spilled to disk behind a `[save-token #id]` notice retrievable in one call via the `save_token_expand` tool, with billed and avoided token metering on a settings dashboard.

File-based cross-session memory: plain Markdown memory files with automatic retrieval injection, format-compatible with Claude Code's CLAUDE.md and memory files, so migrating is a manual file copy.

Connect dsh to a local Obsidian vault: search, read, write, move, and trash notes through `obsidian_*` tools.

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

Standing instructions edited in the DSH settings UI and injected into the system prompt of every subsequent turn.

Built-in Obsidian-style knowledge base for DSH: agents distill conversations, documents and web sources into a structured .wiki graph, with retrieval, graph export, note editing, incremental builds and multi-vault management.

Automatic session retrospective: after a conversation wraps up, distills useful experience into reusable skills stored in the skill library for the model to call, with signal-accelerated triggers, manual runs, an approval mode, and skill-library governance (archive/restore, never deletes directly).

Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.

A markdown notes manager for DSH: full **MD notes manager** and **MD notes editor**, quickly capture conversations into notes, maintain notes by **syncing to Git repositories**, and **bring notes into the conversation context**.

Configuration UI for the official OpenViking memory plugin: connection and user-key setup, local connection diagnostics, a per-session memory toggle in the composer, memory isolation that keeps recall inside the current topic, and recall tuning for score threshold, injected item count, query expansion and excluded URIs.

Context trimmer: lists the current session's context entries with role, preview and ≈token estimate (cl100k), highlights over-threshold items, and removes selected entries exactly without LLM summarization.

Claude Code-inspired Auto Memory meets Codex-inspired Session consolidation, bringing simple, transparent, and context-efficient long-term memory to DeepSeek Harness.

Faithful port of the hermes-agent MEMORY.md / USER.md mechanism for DSH: bounded dual-bank memory (2200/1375 chars), a single `memory` tool (add/replace/remove/batch), frozen-snapshot injection per session, nudge reminders, DSH-native JSON storage — zero external dependencies, zero LLM cost.

Replaces the built-in DSH compaction summarizer with a five-section handoff summary and keeps every shadowed message readable in a segment directory.

Zero-LLM auto-capture and a symbolic \[ENGRAM\] index with progressive disclosure, an ESR-lite task/evidence protocol (esr_task / esr_node / esr_close / esr_link), and per-workspace usage telemetry with an offline recall benchmark (npm run eval).

One shared Obsidian vault for every agent: dependency-free Python core (search/promote/adjudicate/forget), vault template, dsh plugin (memory_search/show/submit/status).

Bounded local memory with CBDC authority gating: SQLite + FTS5 claims, scoped recall with explainable use/verify/ignore decisions and a full audit trail, /memory commands, ≤3-claim/1200-char injection per call, no extra model call.

Bridges the agent to a persistent OKF memory vault over MCP stdio: a Python server (SQLite FTS5 + Markdown) with 10 tools for searching and storing decisions, facts, learnings, conventions, profiles and sources.

Long-term memory for DeepSeek Harness kept as plain markdown, one fact per file, readable in any editor. The `MEMORY.md` index has a hard 200-line / 25 KB cap enforced by `ctx.tools.guard()`: a write that would grow an over-cap index is denied, while a rewrite that shrinks it always passes, so an oversized index can be compacted step by step. The plugin never writes memories on its own — what is kept is decided by you and the model. The same store is also used by Claude Code, Codex, Kiro and OpenClaw.

Honcho memory plugin by Plastic Labs: injects the user profile, session summary and relevant conclusions at session start, uploads each turn to Honcho in the background with secrets redacted, and adds honcho_search / honcho_chat / honcho_remember tools plus a /honcho status command; configured through the ~/.honcho/config.json shared with the other Honcho integrations, against hosted honcho.dev or a self-hosted instance.

Cross-session memory for DeepSeek Harness: agents save, search and update user preferences, facts and project decisions; important entries are injected into later sessions, and a Settings section lists, edits, archives or deletes them.

DeepSeek Harness memory and knowledge hub that routes update, retrieve, and subscribe calls across compatible plugins, with an optional transactional Rust backend.

Session-memory autopilot: watches DSH sessions and extracts OKF entries in-process through the harness LLM (ctx.llm, deepseek-official by default) at idle, commit, compaction and end checkpoints, storing them via the vault MCP server.

Reads the files that AGENTS.md references with @path imports and injects their content into model context at session start, with byte budgets, compaction re-seeding and a six-language settings card.

Long-term memory for DSH agents — durable, inspectable memories with recall, search, browse and knowledge-graph tools, import from ten other AI coding tools, and a settings page.

Local SQLite long-term memory with CJK-aware search, BM25 and character n-gram cosine reranking, deduplication, and lifecycle management.

Native per-workspace memory on the harness's own seams: facts and a bounded always-on profile on the storage-domain JSON unit, approval-gated writes with `(sessionId, seq)` citations, deterministic recall plus session-query FTS over past sessions — no external server, no custom SQLite.

Compresses older DSH context into a structured handoff, retains recent messages, and keeps session history searchable.

Scoped persistent memory for DSH: memory_save/search/replace/remove/list across global, user, project and failure scopes, DSH storage-domain persistence with secret and prompt-injection scanning, session-scope search, retention cleanup, and optional session-start injection; standing context via memory_pin/memory_pins/memory_unpin.

General-purpose knowledge base for DSH: import md/txt/json/yml/docx/pdf, folder management, FTS5 full-text search (BM25), and a Web management UI.

Evidence-bound negative-knowledge ledger: persists disproven paths (command_failed, file_missing) with their outcome and precondition evidence, then warns or blocks repeat attempts until the evidence changes.

Cross-session memory vault: remember / recall / forget tools, per-turn prompt injection, and a settings-page entry browser.

Persistent AI memory backed by a local Obsidian/Codex vault: five obsidian_memory_* read/write/search tools plus a sidebar vault browser.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Memory bridge between DeepSeek Harness and ai-memory: runs ai-memory's finalize-session when a DSH session ends, so the observations it already captured become searchable wiki pages. Skips subagents, queues concurrent session ends, and sweeps sessions abandoned by a forced restart. Requires a separately installed ai-memory server with its DSH lifecycle hooks wired by hand — ai-memory’s own install-hooks does not support DSH; this plugin only finalizes what capture has already recorded.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions, with automatic context injection, archive on clear, and an optional web panel.

Claude Code-style auto-memory, natively: typed memory files (user/feedback/project/reference) with a MEMORY.md index auto-injected into the system prompt (zero footprint when empty); memory_write/read/list/delete follow Claude Code write rules (dedupe-and-update, absolute dates, cross-links); workspace-scoped and user-scoped layers, cross-process file locking with orphan-lock recovery, plain Markdown on disk, no external services, no embeddings.

Human-governed cross-session memory spaces with independent source and consumer relationships, provenance, versioning, and pre-send injection review.

DeepSeek Harness integration for OpenContext with durable cross-session memory, automatic prompt capture and recall, session summaries, structured insights, and document retrieval.

A /remember command that writes facts into the AGENTS.md instruction hierarchy dsh already loads, plus a Memory tab showing which instructions the loader kept within its byte budget.

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.

Make the AI remember how you think, not what you said: actively captures your principles, redlines, and working habits across sessions — with memory capacity, graceful decay, and human-readable reasoning for every entry. 0.7.0 brings an intuitive persona portrait with evidence tracing.

DSH knowledge-graph memory with a better-sidebar tab and a standalone /graph-memory/app dashboard: extracts TASK/SKILL/EVENT nodes, recalls across sessions, and ships as the npm package dsh-graphmemory.

Brain-inspired cognitive plugin: episodic, semantic, procedural and emotional memory with reinforcement-learning signals, a goal stack with time triggers, curiosity-driven autonomous web research and proactive initiatives.

Bi-temporal memory backed by a SodaMem daemon: recall is contributed to the prompt while each turn is assembled and every closed turn is ingested, with no tool call and no model call on the read path; each recalled fact cites the turn it came from and carries validity dates, so superseded facts stop being retrieved.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.

A super-simplified LLM-wiki memory plugin: one index document (auto-loaded) + one markdown file per topic (read only when needed) — no dumping everything into the context and burning tokens. Simple and lightweight, painless to install/uninstall, and freely editable however you like.

Tracks the agent's state as Yogācāra mental factors over a durable seed store, and feeds it back into the prompt as first-person inclination.

Distills session work into background observations and reflections to preserve context across compaction.

Yuque knowledge base as external memory for dsh — auto-injects matching document fragments into conversation, with catalogue search, cloud full-text search and online reading.

ZCode-style persistent project memory with a full settings manager, index-first injection and agent memory tools.

Auto-supplement QMD semantic search when the model greps/globs a knowledge-base directory: zero-dependency DSH plugin, async injection via next-step, no manual invocation.

Local Git-backed long-term memory for DeepSeek Harness with hybrid CJK/English retrieval, cited context, transactional sync, previews, and rollback.

Dual-ledger cross-session memory: auto-extracts lasting facts from conversations into MEMORY.md and maintains a PROGRESS.md project ledger, recalling both into every new session.

Knowledge-base-driven agent preset: wiki long-term memory, a web KB UI, a management page and optional UI polish.

Workspace-wide sticky notes on an infinite canvas: notes are plain Markdown files, created manually, captured from conversations, or distilled by the AI, and can be handed back as context; ships 12 model tools and 5 bundled skills for creating, tagging, arranging, comparing and merging notes.

An Obsidian-style knowledge base: ingest sources, let the LLM build and maintain an interlinked wiki, and ask questions grounded in it.

Local-first Agent Experience Network for DeepSeek Harness, distilling task-level experiences from traces and live manifests, grading by H0-H4 evidence, discovering by compatibility, and promoting only after explicit review.

DSH-native integration layer for the Minta memory engine: composes the official dsh-mcp-client row, registers the minta-memory-governance skill plus a session-start memory prewarm, and ships a Minta agent preset; requires the separately deployed Minta engine (Python/Docker) to provide the 19 MCP tools - not usable without it.

Notion connector for DeepSeek Harness: search, read, query, create, update, and append Notion pages and databases via six agent tools, with a Web settings page — configured once with an Integration Token.

Cross-session memory for the model: full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context.

Layered file memory for DeepSeek Harness with workspace-scoped USER/MEMORY notes, background consolidation, and hybrid session recall.

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Generate AI-narrated DSH session reports (daily/weekly/monthly, any date range) and sync them to flomo (浮墨笔记) with one configurable tag (default #write/dsh) and automatic # stripping, via a web settings panel with daily reminder.

Read-only bridge that surfaces Claude Code's existing project memory in DSH — git-root-aware resolution, credential redaction before injection, and an on-demand recall tool. Zero runtime dependencies.

Forgetting-curve in-place dialogue compression for DeepSeek Harness: recent turns stay verbatim, middle turns are structurally dehydrated (zero-LLM), ancient turns fold into a bounded summary pair — unbounded conversations on a bounded memory budget.

Connect Trilium notes to the DSH agent via ETAPI with 20 agent tools: durable memory (remember/recall + auto-injected index), note management (CRUD/clone/attributes/revisions), full-text search, weekly-report workflow, attachments, calendar notes, backup/import, and a settings card.

Write notes and memos to flomo (浮墨笔记) from any agent via the flomo_send tool, configured once with the flomo API URL or API Key.

Memory Lake as a persistent memory layer for dsh: memory_search, memory_remember, and memory_forget tools over the memorylake CLI, a session status line, and guided setup/diagnostic skills, sharing one ~/.memorylake identity and memory set with the Claude Code and Codex plugins.

DSH side of the dsh-ecolink memory ecosystem: bridges chat.deepseek.com and DeepSeek Harness through a browser extension that harvests DSM-format memory tags and injects recalled memories into web chats, a zero-dependency local service that writes a shared memory pool, and this adapter, which injects memories pre-step and offers /ecolink-push write-back; compression is transactional (staging pool with commit/rollback).

Memory triage for DeepSeek Harness: at the end of each turn it decides which entries to keep and which to archive, routes project-specific ones into a project bucket while global ones stay in the main store, merges near-duplicate entries, and falls back to an LLM when the rules are unsure — automatic actions are recoverable archives only, never deletions.

Cross-session event-cue memory for DeepSeek Harness: auto-extracts task/conversation cues and user language habits from every turn into a persistent global cue bank, then re-injects remembered context on topic-switch detection (keyword or vector matching).

PostgreSQL-backed durable memory for DSH agents: MCP memory tools plus a Web panel for reviewing memories and candidates.

Persistent memory for DeepSeek Harness with curated facts, automatic turn retention, and graph- and vector-ranked recall.

Feeds every dsh prompt into the local agent-feedback-loop feedback-memory pipeline — captures dissatisfaction, reviews it offline into reflections, and attaches the compiled recurrence-rule context back to the turn, never blocking a prompt. Requires the agent-feedback-loop runtime; running agent-feedback-loop install afterwards wires existing dsh profiles automatically.

Personal-experience memory for DSH: turns solved tasks into sourced problem cases with condition-scoped claims, recalls them into new tasks via hidden pre-step injection, and makes corrections/deletes cascade to future recall.

Knowledge base with a corrective acquisition loop for DeepSeek Harness: when the agent keeps hitting the same failure, a background worker fetches the web under a rate limit, distills the result into a staging area, and only a two-stage commit makes it recallable — pages without sources are refused.

Connects DeepSeek Harness to a local SiYuan (思源笔记) desktop app: registers its note tools as mcp__siyuan__<tool>, exposes the AI configured in SiYuan together with its agent loop as one more tool, ships a notes skill, and enforces a readonly/authoring/full profile on every call while keeping the tool list available when the app is closed.

Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.

Registers the local flowix-cli MCP server so the agent can search, read, create, and edit Flowix memos and mind-map artifacts.

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

Causal memory for dsh: a zero-dependency MCP stdio bridge that mounts the 17 tools of the causal-memory server under clean names (no mcp__ prefix) — decision → outcome edges with typed relations (caused / enabled / prevented) in a local SQLite store that survives compaction — plus a pinned system-prompt section. Requires the causal-memory server binary on PATH (pip install causal-memory, or a prebuilt release).

Local Obsidian vault as the agent knowledge store, with read-only DSH tools that route status, preference, correction, memory, project, search, and suggest to the matching page.

Automatic conversation distillation: background subagent reflection + skill create/update.

Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and session memory for DeepSeek Harness: memsearch/memfind/memread/membrowse/memgrep/memglob over viking:// URIs, memadd/memremove resource management, memqueue observer status, memcommit session capture, and memlearn skill playbook minting.

Automatic context compression for DeepSeek Harness: compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.

The memory organ of Agent-Body: after 2 minutes of silence it enters light sleep and after 5 minutes deep sleep, where deterministic rules distil real experience into memory cards (pitfalls, playbooks, hotspots, unresolved issues, facts). Incoming commands recall related cards by keyword and inject them into context; cards unused for long decay on a half-life and are archived rather than deleted. It also de-noises body-wide homeostasis warnings: repeats inside a window are counted instead of re-printed, and a warning that keeps recurring without ever healing converges into a known steady-state offset and goes quiet. Consolidation and recall make no model calls.

ShiGuang Memory Engine (SGME) bridge: multi-agent shared long-term memory via HTTP — L0/L1/L1.5/L2 distillation, scenario-based injection, unified search, and proactive care signals (memory_search / wiki_search / signal_pull / signal_claim / signal_ack), installable as `dsh-sgme`.

Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona, auto recall injection, skill synthesis, fully local (SQLite FTS5 + jieba, optional vector recall).

Adds a multi-user settings panel to the DSH web client: usage-mode selection, member management with online status and device binding, and switching or sharing of per-member memory and knowledge bases.

Cross-session memory with zero-token deterministic recall (bigram-Jaccard fused with FTS5 BM25 via RRF, Chinese-aware tokenization), reinforcement that strengthens repeated observations, and procedures crystallized into SKILL.md files refined in place through an active-stale-archived lifecycle with reversible archive and rollback. Ingest and disposal each expose a user-chosen autonomy tier; conflicts and high-importance writes always go to human review, and nothing is ever auto-deleted. Requires Node 22.5+.

One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.

Cross-session memory plugin for DSH (v0.6.1, npm @asherliner/dsh-memory-connect): auto-extraction, SQLite FTS5 indexing, RRF semantic recall injected into the system prompt every turn, scheduled maintenance, LLM-powered consolidation via ctx.llm, context explosion prevention, and global Soul identity via ~/.dsh/soul.md. v0.5.0 added temporal context graph (valid_from/valid_until/supersedes, append-only corrections via reviseMemory), trust model (recalled history injected as untrusted reference, current instruction always wins), turn-end summarization. v0.6.0 added local semantic embeddings (BAAI/bge-small-zh-v1.5 via embed_server.py, cosine + RRF fusion with FTS5, no cloud calls, ~232 msgs/sec on CPU). v0.6.1 fixed ~ expansion in path config. Zero-config install.

Biomimetic memory system for DeepSeek Harness: a single SQLite store (node:sqlite, WAL) whose Markdown tree is kept as a read-only mirror; memory tools, frozen-snapshot injection at session start, graded approval gating, on-demand extraction of the current session, near-duplicate merging, an archive and supersede lifecycle, memory metabolism (dream), memory pins, semantic recall over local embeddings, and the /memory command.

Karpathy LLM Wiki pattern knowledge base for DSH: wiki-write/wiki-search skills, zero-dependency pipeline (lint/index/mnemon memory sync/quality feedback), minimal lifecycle plugin injecting schema + knowledge preview, SiliconFlow semantic recall via an Ollama-compatible proxy.

Portable agent knowledge base in plain OKF v0.2 Markdown: 13 wiki_* read/write tools, progressive disclosure, backlinks, gated writes via AGENTS.md rules, auto index/log maintenance, linting, and named multi-bundle switching (session-level or global).

Governed long-term memory for DeepSeek Harness: append-only evidence ledger with write guards, 7-tier authority claims, supersede chains, and budgeted pre-step injection with per-domain quotas.

Persistent five-layer memory system with relevance injection, LLM auto-extraction, profile rotation, and six agent tools.

Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with templates, a gate that blocks writes to protected files without a one-time approval token, zero-judgement event logging, weekly distillation, and a TDD execution-loop skill.

DSH ↔ agentmemory session-memory bridge: mirrors session lifecycle into a local agentmemory daemon (REST), exposes memory_recall / memory_remember tools, and injects a per-session memory context window via agent/pre-step.

An accumulated design-taste corpus for DSH agents: feed good and bad examples, distill principles, and review new designs against learned judgment rather than a fixed ruleset.

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.

Fully local vector memory for DSH: local embeddings, SQLite storage, automatic recall injection, dedup with conflict detection, soft-delete recycle bin, online backup, and optional LLM extraction.

Build auditable KB packs (SQLite FTS5) from md/txt/docx/pdf with deterministic retrieval and original-text reading.

Reading archive for dsh: after reading open-source code, capture quick notes or write full deep notes that group into one card per repo / file / symbol, stored as an append-only log of Markdown notes you can open in Obsidian; query your history, browse recent reads, or search your own Obsidian vault and link related notes to a reading record. Nine tools, a /codevault command, and a code-reading skill.

Cross-session memory for DeepSeek Harness via the official storage domain: memories persist through ctx.storage (storageDomain table) and are injected into the system prompt through a registered section (memory:recall), with memory_save / memory_forget tools so the agent reads and writes its own memory (maxMemories configurable).

Memory protocol enforcement plugin: bridges the opencode-memory MCP server, forces memory_weave before tool calls, auto-ingests turns, and injects memory context into agent steps.

Self-maintaining handoff memory per working directory and git branch: records turns, folds them into concise Markdown, and injects the result into future sessions from ~/.agent/agent-handoff, byte-compatible with pi-handoff.

Three-layer local memory for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md) read on demand through the memory_* tools + L2 searchable knowledge base (facts + SQLite FTS5, Chinese search via sliding-window tokenization) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and from approved Agent Hub documents (memory/global, memory/projects, accepted decisions) with content-hash dedup. v0.2.0 removed every automatic injection: memory enters the context only when the model calls one of the 12 memory_* tools, and data stays on the local drive.

Offline QR code (SVG/PNG/ASCII) and barcode (Code128/EAN-13) generator for DeepSeek Harness, no network and no shell.

Scans the skills visible to the current session and ranks them by relevance to the recent conversation.

Local-memory lifecycle for the official Hindsight plugin on DSH desktop: one-click start/stop of the hindsight-embed daemon, auto-start on boot, stop on exit, hides the uv.exe console window, and installs the vault/models to another drive.

BM25 keyword-based memory recall.

Context manager for DeepSeek Harness: auto-summarizes every turn into priority-sorted records, injects them plus pinned cross-session notes and custom text into each model request, and folds any-size real conversation ranges into summaries to save tokens. Persistent and restart-safe. NOTE: manual multi-step install — copy the three package folders into profiles/node_modules and add the provided cordis.patch.yml rows, then restart DSH; not a standard one-command install.

Hana-style assistant manager for DSH: visual preset management (cards, yuan personalities, avatar cropping) plus a full Hana memory stack (rolling summaries, layered compilation, SQLite fact store, deep memory).

Agent tools for a self-hosted mem0 server: add, search, get, update, delete, history, reset and status memories, with a settings-panel configuration card.

Project+global long-term memory for the dsh web GUI: split POST /items endpoints, tool-call context merged into memory items as compact summaries, with deduplication and session-scoped persistence.

SQLite memory entries, a calendar with due-time reminders, and cron-scheduled agent tasks, with 13 model tools and a bilingual zh/en UI.

A local-first personal state record and decision engine for dsh: keeps every input byte-for-byte with line-level provenance, argues against its own conclusions by generating defeaters first, ages each stored fact with its own TTL, and reports where a decision rests on nothing at all.

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba retrieval backs it, and a scenario-level fidelity regression suite gates releases.

Local, auditable personal memory for DeepSeek Harness: preferences, project conventions, workflows and error lessons persisted as a changelogged JSON file in the workspace, with onboarding, auto project-convention extraction and evidence-backed lessons.

Model-authored context pruning for DeepSeek Harness through the official compaction API.

Coding retrospect distilled memory for DSH: distills rejected solutions, pitfalls and constraints from each turn via a local LLM, tags them into MemOS (type:rejected_solution), and boosts weighted recall on coding tasks via agent/pre-step.

Project documents and long-term memory as plain Markdown in a dedicated Obsidian vault: six mem_* tools (search, read, write, log, brief, admin), one budgeted recall injection at the first step of a session, and automatic distillation of completed turns. Obsidian does not need to be running, and the vault stays readable with the plugin uninstalled.

Project-scoped persistent key-value memories with set/get/list/delete/search model tools and JSON-file storage.

Rewrites each request against a learned prompt profile and automatically updates habits, anti-hallucination rules, and learning records.

Cited memory over DSH's lossless session log: distilled facts carry `(sessionId, eventRange)` citations that expand back to the exact original log excerpt.

Memory Standard Protocol (mm) for DeepSeek Harness: layered MEMORY.md with hard budgets, frozen snapshots, mm:// URI interop, session-log digestion, mem_* tools and a standalone CLI.

Cross-session experience memory for DSH. Lessons are evidence-graded, injected when the turn is about the same thing, and shown just before an action only when the record declares which call it applies to. A rule that holds whatever the turn is about — "always answer in Chinese" — can be marked **standing** and is then carried every turn: measured on 24 isolated real-model turns, a standing rule is followed 6/6 against 0/18 for the controls (empty store, same record unmarked, unrelated standing record). A guess still cannot become always-on: a standing record needs a verified passage like any other. What nobody looks up is retired, reversibly. Five tools, seven slash commands, zero runtime dependencies.

Cipher memory platform as a DSH bundle: four memory types (attention, experience, preference, cognitive) sedimented per turn by four memory agents, cross-session deterministic recall injected via systemPrompt.context, insight review kept out of user-facing output, per-session UNNI/LOOP modes with memory-driven auto-continuation, memory search/ingest tools, plus a settings page (SOUL editor) and an AgentPool panel.

Persistent project memory, event-sourced task lifecycle, context budgeting, and cooperative multi-agent handoffs.

Mnemosyne memory for DeepSeek Harness: remember / recall / forget / stats / sleep tools, embedded skill, auto-setup, optional auto-sync/prefetch, and a Settings panel. Data lives under ~/.dsh/mnemosyne.

Cross-app project memory for DeepSeek Harness with role-separated writeback, a visual knowledge workspace, confirmed corrections, session controls, local Writer and organizer settings, and an account-free Windows local installation preview.

Bridges the MemOS memory service over MCP: the agent gets add/search/update/delete memory, multi-cube sharing, and a memory scheduler as mcp__memos__* tools.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society agent runtime, and six yogacara seed skills.

View and delete persistent skill memory from the DSH sidebar.

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

Persistent memory for DeepSeek Harness: memory read/write/retrieve tools, per-turn auto-recording, project-scoped recall injection and a management UI, with non-destructive Claude Code memory import.

Decision log for DeepSeek Harness: record key decisions (chosen option + why) into a versionable DECISIONS.md via decision_log / decision_list / decision_audit tools, and auto-inject the summary into future sessions so decisions stay traceable and are never re-litigated.

Long-term memory for DeepSeek Harness, read-only as of 0.1.0: a scribe_recall tool that reads a plain-markdown memory room, path rules that refuse directory traversal, Unicode smuggling and NTFS alternate data streams, and a bounded index whose truncation is always reported rather than silent.

Native DSH foundation bundle that registers a persistent default workspace, provides paged read-only inspection of plugins, skills, memory, sessions, storage, settings, credentials, and DSH_HOME files, and synchronizes rich CLIProxyAPI model capabilities into native provider settings.

Permanent memory plugin for DSH with vector search, LLM reflection, and knowledge pages.

Integrated memory and context management plugin: four-layer memory system (L2-L4), context compression/trimming/freezing, prompt orchestration, input box UI buttons, and enterprise security with role-based access control.

Persistent conversation memory for DeepSeek Harness: memory tab, automatic AI naming, per-AI privacy isolation, sidebar AI names, and automatic experience archiving. A static profile plugin available in every preset without disappearing on restart.

File-backed working memory: memorize/recall key premises verbatim in a session notes file so they survive context compaction losslessly.

Bridge into a global Markdown knowledge base shared with the Codex kb.cmd CLI: kb_add/kb_search/kb_show/kb_timeline tools with byte-compatible frontmatter.

Post-compaction premise-drift guard: injects a one-shot notice when a compaction summary drops a critical literal anchor.

Injection scheduler for DeepSeek Harness injection planes: cross-plugin sections register/order/account on the official storageDomain, with conflict detection and per-session budget summaries (B10 panel data source).

Hindsight long-term memory for DeepSeek Harness: injects relevant memories before each turn and retains finished turns to a Hindsight bank.

Advanced memoria tools: session context injection (profile + recall), recent decisions, health report, namespace allowlist, memory relation graph, and entity search; companion to dsh-memoria.

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and oversized content through the official ctx.compaction seam.

Organize folders and sessions into projects with shared PROJECT.md memory and AGENTS.md instructions injected into every session, plus a project tree sidebar.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

Tiered persistent memory (user/env/project) with per-tier char budgets and semantic query routing; full layers refuse writes instead of silently evicting.

Project-level Local Context Engine for DeepSeek Harness: retrieval/compression/prioritization over history, code, files, user preferences and agent trajectories, producing a dynamic context window for any LLM.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.

Layered cross-session memory for DSH that pushes only what changed. The first round injects every active entry, later rounds push only added / updated / removed ones, and nothing at all is injected when nothing changed. Facts and decisions carry semantic keys (one active truth per key), the model may only write to an inbox that a human promotes, an entry can carry a review date that raises a one-time reminder when it comes due, search is relevance-ranked with Chinese matched by bigram, and a sidebar tab tells the lifecycle story instead of just listing files — entries are grouped into awaiting confirmation / in use / archived, viewable by type, tag or date, and the tab can promote a candidate, withdraw or archive a standing entry, restore an archived one and delete a candidate, alongside the global and workspace instruction files and the current injection size. A zero-dependency CLI ships with it, so the store is usable without DSH.

Persistent long-term memory for DeepSeek Harness: a JSON store of typed entries (fact, preference, entity, rule, episodic) exposed as the memory_remember and memory_recall agent tools, with recall ranked by keyword overlap, importance and access frequency.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

Coordinates bounded project recall from compatible memory and learning providers, with shared settings and provider lifecycle management.

Project-scoped local memory with review-before-recall, source references, reversible consolidation, and a portable Cordis service; the Harness adapter provides search and settings, with optional Brain integration.

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are blocked, and cognition persists across sessions (47 upstream-verified fixes, gold-free 20-task run).

Per-workspace memo/todo panel that auto-captures queued and running user instructions, marks preempted tasks as interrupted, and restores them to their previous state with one click.

Keeps notes as local Markdown files grouped by directory under a root folder you choose, with a sidebar page, AGENTS-style rule files surfaced as writing context, and six agent tools.

Shared engineering skills, a read-only memory-bank dashboard with SQLite audit guidance, and workflow request previews for DSH.

Local relationship-memory workbench with a confirmation gate: every AI write — extracted memories and newly created contacts alike — lands in a pending queue until the user confirms it in the GUI; materials are archived verbatim with quote-level provenance checks on AI extraction, and confirmed memories aggregate into per-contact timelines, gift occasions and reciprocity views. Ships a native relationship agent preset for conversation capture; JSON storage by default with an optional SQLite backend, zero production dependencies.

Memory archive and prompt viewer for DeepSeek Harness: read back what compaction folded out of context - browse past sessions or Tavern playthrough archives (summary, original text, state) with full-text search - and inspect the prompt each turn actually sent, listing every assembled system section with its order, character count, offset, hash and mutability, plus an assembly map, registry export, and honest diagnostics when a section is empty or its log cannot be read. Optionally provisions a roleplay agent preset.

Single-file persistent companion memory: interests, preferences, tasks, and past works summarized into the system prompt, with read/update tools.

Read-only enhancer for a file-based long-term memory library (markdown cards in git): a memory_find search tool, a small budgeted memory digest injected into the system prompt, and a settings page with library overview, health-check status and toggles.

Action-state time memory: record typed states and actions, then analyze trends, anomalies, and causality.

PowerContext for DeepSeek Harness: WorkBuddy-style project memory and inspectable handoff workflows - bounded context recall before each model step, 19 pc_* tools for memory, handoff, experience and skills, with a Windows server watchdog for resident operation.

Background memory consolidation (auto dream) for DeepSeek Harness: periodically reviews recent sessions and existing memories to dedupe, refresh stale entries, remove contradictions and rebuild the MEMORY.md index, with hybrid/volume auto triggers, /dream command and a settings-panel config card.