MIT-licensed, local-first agent memory core that loads natively into DeepSeek Harness via the Cordis plugin lifecycle — typed knowledge graph, cross-session auto-recall and gm_* tools over SQLite, with optional vector retrieval.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
MIT
01What can it help you accomplish?
Give DeepSeek Harness agents durable, traceable cross-session memory
A typed knowledge graph (TASK / SKILL / EVENT nodes with typed edges) in local SQLite, with relevant memory automatically recalled in new sessions — even after DSH restarts
DeepSeek Harness users who want their agent to remember past tasks, fixes and reusable skills across sessions
Shrink context by recalling only relevant memory instead of replaying full history
A relevant local subgraph injected into the prompt during Prompt Assembly; the author's seven-turn benchmark measured an ~75% token reduction at turn R7
DSH users hitting context limits or paying for redundant history replay in long workflows
Explicitly record and search long-term knowledge inside DSH
gm_record persists TASK / SKILL / EVENT nodes deterministically; gm_search runs long-term graph search; gm_status and gm_stats expose store and graph state
DSH users who need deterministic control over what critical knowledge is remembered and why a memory was recalled
02How to install into DeepSeek Harness
Prerequisites
- Node.js `22.19+` or `24+`
- DeepSeek Harness (dsh) with the web profile — the README uses `npx @deepseek-ai/dsh`; local acceptance was tested on DSH `0.1.0-rc.5`
Installation steps
- 01
Clone and build the tarball from source (the beta is not on npm yet): `git clone https://github.com/adoresever/graph-memory.git && cd graph-memory && npm install && npm test && npm run build && npm pack`
$ git clone https://github.com/adoresever/graph-memory.git && cd graph-memory && npm install && npm test && npm run build && npm pack
- 02
Install the generated tarball into the DSH web profile: `npx @deepseek-ai/dsh plugin --profile web add /absolute/path/to/graph-memory-1.6.0-beta.1.tgz`
$ npx @deepseek-ai/dsh plugin --profile web add /absolute/path/to/graph-memory-1.6.0-beta.1.tgz
- 03
Optionally dump the config to confirm registration: `npx @deepseek-ai/dsh --profile web --dump-config`
$ npx @deepseek-ai/dsh --profile web --dump-config
- 04
Start DSH web: `npx @deepseek-ai/dsh web`
$ npx @deepseek-ai/dsh web
- 05
Optional vector retrieval: export `GRAPH_MEMORY_EMBEDDING_API_KEY`, `GRAPH_MEMORY_EMBEDDING_BASE_URL`, `GRAPH_MEMORY_EMBEDDING_MODEL`, `GRAPH_MEMORY_EMBEDDING_DIMENSIONS` before `dsh web`
$ dsh web
Verify the integration
- Confirm that `graph-memory/dsh` is enabled under Settings → Plugins → Plugin list
- Use `gm_status` to check store path, graph counts, vector coverage, mode, and dimensions
03DSH integration and capability boundaries
Native DSH plugin loaded by the Cordis plugin lifecycle via the cordis.patch.yml bundle entry — registers gm_* tools, auto-recall during Prompt Assembly, and DSH Credentials access
Typed knowledge-graph memory core
DSH session conversation events→TASK / SKILL / EVENT nodes with typed edges (USED_SKILL, SOLVED_BY, REQUIRES, PATCHES, CONFLICTS_WITH) plus episodic provenance, stored in local SQLite
Writes a local SQLite database at $DSH_HOME/graph-memory/graph-memory.db (normally ~/.dsh/graph-memory/graph-memory.db)Dual-path recall with graph ranking
the current user query during Prompt Assembly→a deduplicated relevant local subgraph (vector or FTS5 search + community expansion + Personalized PageRank) injected into the prompt
Optional network calls to OpenAI-compatible embedding providers (DashScope, OpenAI, local) when vector retrieval is configuredgm_* tools for record, search and observability
explicit agent or user tool calls inside DSH→gm_record persists knowledge deterministically; gm_search runs long-term graph search; gm_status and gm_stats report store, extraction, recall, vector and community state
gm_record writes new nodes into the local graph storeSafe, local-first context assembly
recalled memory nodes→recalled history injected as untrusted reference material that cannot override current user instructions
Memory data stays in the user's local profile by default; API keys come from host credentials or environment variables, never the database
04Who is it for? When not to use it?
Good for
- DeepSeek Harness users who want their agent to remember past tasks, fixes and reusable skills across sessions
- DSH users hitting context limits or paying for redundant history replay in long workflows
- DSH users who need deterministic control over what critical knowledge is remembered and why a memory was recalled
Not for
- The current build is 1.6.0-beta.1 and DeepSeek Harness is still in Developer Preview, which may introduce compatibility-breaking changes; local acceptance was tested on DSH 0.1.0-rc.5.
- npm registry publication is pending, so installation requires cloning the repository and building the tarball from source instead of a one-command npm install.
- Automatic extraction depends on auxiliary-model output stability, so critical knowledge should be persisted explicitly with gm_record; DSH does not yet expose gm_update and gm_maintain.
05Compatibility, maintenance and safety notes
- The current build is 1.6.0-beta.1 and DeepSeek Harness is still in Developer Preview, which may introduce compatibility-breaking changes; local acceptance was tested on DSH 0.1.0-rc.5.
- npm registry publication is pending, so installation requires cloning the repository and building the tarball from source instead of a one-command npm install.
- Automatic extraction depends on auxiliary-model output stability, so critical knowledge should be persisted explicitly with gm_record; DSH does not yet expose gm_update and gm_maintain.
MIT · actively maintained (last push 2026-08-14; current beta 1.6.0-beta.1)
06Frequently asked questions
How does Graph Memory integrate with DeepSeek Harness — native or MCP?
Native. It is loaded by the DSH/Cordis plugin lifecycle via the cordis.patch.yml bundle entry and integrates the Session, Tool, Agent Loop, Prompt Assembly, LLM, and Credentials seams — it is not simulated through an MCP side channel, and no DSH fork is required.
What do I need before installing?
Node.js 22.19+ or 24+ and DeepSeek Harness. The current beta is not yet published to npm, so you clone the repository, run `npm install`, `npm test`, `npm run build`, `npm pack`, and install the generated tarball with `npx @deepseek-ai/dsh plugin --profile web add`.
Do I need an embedding API key?
No. Embeddings are optional — without them, recall falls back to FTS5 lexical search. If you want vector retrieval, set the GRAPH_MEMORY_EMBEDDING_* environment variables for any OpenAI-compatible provider (DashScope, OpenAI, or local providers).
Where is my memory data stored?
In a local SQLite database at $DSH_HOME/graph-memory/graph-memory.db (normally ~/.dsh/graph-memory/graph-memory.db). Data stays in your local profile by default, and API keys come from host credentials or environment variables, never from the database.
What are the current limitations?
The plugin is at 1.6.0-beta.1 and DeepSeek Harness is in Developer Preview, so compatibility-breaking changes are possible. DSH does not yet expose gm_update and gm_maintain, and the Pro visual graph workbench is not shipped yet.
07Related DSH workflows
weknora
by tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
honcho
by plastic-labs
Memory library for building stateful agents
mirage
by strukto-ai
The World's First Virtual Terminal for AI Agents
reme
by agentscope-ai
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
08Data and sources
Loaded by the DSH/Cordis plugin lifecycle, not simulated through an MCP side channel.
Integrates Session, Tool, Agent Loop, Prompt Assembly, LLM, and Credentials seams.
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.