by adoresever
Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse
# Add to your Claude Code skills
git clone https://github.com/adoresever/graph-memoryGuides for using ide extensions skills like graph-memory.
Last scanned: 5/16/2026
{
"issues": [
{
"type": "npm-audit",
"message": "esbuild: esbuild enables any website to send any requests to the development server and read the response",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "openclaw: OpenClaw Vulnerable to Local File Inclusion via MEDIA: Path Extraction",
"severity": "critical"
},
{
"type": "npm-audit",
"message": "vite: Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vite-node: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vitest: Vulnerability found",
"severity": "medium"
}
],
"status": "FAILED",
"scannedAt": "2026-05-16T06:23:15.575Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}See how graph-memory compares with popular alternatives.
graph-memory is an open-source ide extensions skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by adoresever. Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse. It has 627 GitHub stars.
graph-memory failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.
Clone the repository with "git clone https://github.com/adoresever/graph-memory" and add it to your Claude Code skills directory (see the Installation section above).
graph-memory is primarily written in TypeScript. It is open-source under adoresever on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other IDE Extensions skills you can browse and compare side by side. Open the IDE Extensions category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh graph-memory against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Graph Memory owns the model-visible historical surface without deleting DSH's event log. By default it keeps the newest five completed user turns, removes completed reasoning/tool traces from future requests, and recalls relevant older or cross-session source Q/A automatically.
| Before | Now |
|---|---|
| Extract TASK / SKILL / EVENT directly from messages | Create one self-contained turn summary, then derive SPO from that same sentence |
| Graph nodes could become the factual payload | Summary, SPO, and communities only navigate; original question and final answer remain the evidence |
| Old memories from the active session could be filtered wholesale | Exclude only sources still visible in the fresh window; archived same-session and cross-session recall share one path |
| Community expansion could pull a whole neighborhood | Local LPA narrows candidates, query-time PPR ranks them, and only matched Q/A is recovered |
| DSH retained complete tool and reasoning traces | Completed turns retain question + final answer; older prefixes collapse to one fixed marker |
Writing one completed turn costs exactly one auxiliary LLM call. Community detection and PPR are local. There are no hard-coded node/edge counts, semantic direction gates, or JSON repair that turns invalid output into accepted data. Read the complete design, source map, and porting sequence →
| Real 20-turn GLM-5.2 run | Historical native DSH baseline | Latest Graph Memory | Change |
|---|---|---|---|
| T20 first request | 56,998 tokens | 11,008 tokens | −80.69% |
| T20 model-visible messages | 171 | 21 | −87.72% |
| T01–T20 first-request context | 532,451 tokens | 165,896 tokens | −68.84% |
| All measured tokens¹ | 2,487,776 | 2,327,728 | −6.43% |
¹ The latest candidate includes 166 main-agent requests, 20 turn extractions, and 41 embedding requests; the historical baseline made 77 main requests. DSH commits and nondeterministic tool loops differ, so this is not a simultaneous strict A/B. First-request context is the direct takeover metric; the full bill remains visible.
20/20 scenario turns passed · 20/20 structured extractions succeeded · 0 quarantined · 20 turn summaries · 92 SPO triples · 30 communities · 20 summary vectors. T11, T19, and T20 automatically recalled out-of-window memory with exact source question and final answer.
Read the Markdown benchmark, per-turn data, method, and limits →
The graph is a navigation layer, not a replacement for evidence. TASK, SKILL, and EVENT nodes point back to the original user question and final visible answer; recalled context includes those exact source messages.
Node.js 22.13+ · no DSH fork · until npm 1.6 is published, install the pinned GitHub release:
npx @deepseek-ai/dsh plugin --profile web add github:adoresever/graph-memory#v1.6.0-beta.16
npx @deepseek-ai/dsh --profile web --dump-config
npx @deepseek-ai/dsh web
The npm registry still serves the old 1.5.8; do not use it to validate DSH. Switch to npx @deepseek-ai/dsh plugin --profile web add graph-memory only after npm view graph-memory version reports 1.6.0-beta.16 or newer.
Confirm that graph-memory/dsh is active under Settings → Plugins. The default database is $DSH_HOME/graph-memory/graph-memory.db, normally ~/.dsh/graph-memory/graph-memory.db.
| Capability | Implementation |
|---|---|
| Context takeover | Configurable newest-N completed turns; one archive marker replaces the older model surface |
| Lightweight extraction | Only the user question and final answer; strict structured tool contract; no reasoning/tool transcript ingestion |
| Query-first recall | Vector Top-K with FTS5 fallback; exact source Q/A travels with graph hits |
| Durable memory | Local SQLite, stable provenance, cross-session and cross-project recall |
| Failure behavior | Invalid extraction is quarantined; foreground conversation continues; bad data is not repaired or persisted |
| Host support | Native DSH/Cordis adapter; maintained OpenClaw Context Engine adapter |
Graph Memory supports OpenAI-compatible embedding endpoints. Without embeddings it falls back to FTS5 and does not block conversation.
export GRAPH_MEMORY_EMBEDDING_API_KEY='replace-with-your-key'
export GRAPH_MEMORY_EMBEDDING_BASE_URL='https://dashscope.aliyuncs.com/compatible-mode/v1'
export GRAPH_MEMORY_EMBEDDING_MODEL='text-embedding-v4'
export GRAPH_MEMORY_EMBEDDING_DIMENSIONS='1024'
dsh web
| Tool | Purpose |
|---|---|
gm_status |
Store, extraction, recall, vector, and retention state |
gm_search |
Explicit graph-memory search |
gm_record |
Deterministically persist a TASK, SKILL, or EVENT |
gm_stats |
Graph and retention receipts |
gm_maintain |
One bounded maintenance tick |
gm_retry_extraction |
Explicitly retry quarantined extraction |
Automatic recall needs no tool call. Extraction may use a dedicated model via GRAPH_MEMORY_LLM_PROVIDER and GRAPH_MEMORY_LLM_MODEL; optional reasoning and output controls are GRAPH_MEMORY_LLM_REASONING_EFFORT and GRAPH_MEMORY_LLM_MAX_TOKENS.
openclaw plugins install graph-memory
openclaw plugins enable graph-memory
openclaw gateway restart
Activate the Context Engine slot in ~/.openclaw/openclaw.json:
{
"plugins": {
"slots": { "contextEngine": "graph-memory" },
"entries": { "graph-memory": { "enabled": true } }
}
}
The repository also contains an experimental read-only DSH Pro Lite Host + Client plugin backed by Community SQLite. The 2D/3D graph workbench, split view, and controlled drag-to-context remain planned. See dsh-pro/README_CN.md.
Current beta 1.6.0-beta.16 passes 138/138 automated tests, both TypeScript builds, npm package verification, and a real 20-turn run against the latest DSH source.
Reproduce it from benchmarks/dsh-context-takeover/. Raw conversations, provider responses, local paths, and credentials are excluded.
npm install
npm test
npm run build
npm run verify:package
MIT © 2026 adoresever · Asset and trademark notes