AI SummaryLocal GraphRAG knowledge base backed by SQLite + MNN embeddings. Fully compatible with Android OfflineAI RAG database format. On first use, (~400 MB) is auto-downloaded into .
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "py_mnn_kb" skill in my project. Please run this command in my terminal: # Install skill into your project (9 files) mkdir -p .claude/skills/py-mnn-kb && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/py-mnn-kb/SKILL.md "https://raw.githubusercontent.com/openclaw/skills/main/skills/er6y/py-mnn-kb/SKILL.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/py-mnn-kb/README.md "https://raw.githubusercontent.com/openclaw/skills/main/skills/er6y/py-mnn-kb/README.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/py-mnn-kb/_meta.json "https://raw.githubusercontent.com/openclaw/skills/main/skills/er6y/py-mnn-kb/_meta.json" && mkdir -p .claude/skills/py-mnn-kb/assets && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/py-mnn-kb/assets/example_stop.json "https://raw.githubusercontent.com/openclaw/skills/main/skills/er6y/py-mnn-kb/assets/example_stop.json" && mkdir -p .claude/skills/py-mnn-kb/assets && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/py-mnn-kb/assets/example_terms.json "https://raw.githubusercontent.com/openclaw/skills/main/skills/er6y/py-mnn-kb/assets/example_terms.json" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/py-mnn-kb/config.example.json "https://raw.githubusercontent.com/openclaw/skills/main/skills/er6y/py-mnn-kb/config.example.json" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/py-mnn-kb/requirements.txt "https://raw.githubusercontent.com/openclaw/skills/main/skills/er6y/py-mnn-kb/requirements.txt" && mkdir -p .claude/skills/py-mnn-kb/scripts && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/py-mnn-kb/scripts/py_mnn_kb.py "https://raw.githubusercontent.com/openclaw/skills/main/skills/er6y/py-mnn-kb/scripts/py_mnn_kb.py" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/py-mnn-kb/skill.json "https://raw.githubusercontent.com/openclaw/skills/main/skills/er6y/py-mnn-kb/skill.json" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Local vector knowledge base with GraphRAG retrieval (vector + BM25 + knowledge graph). Use this skill when the user mentions: "查知识库", "加入知识库", "记住这个", "save to KB", "add to knowledge base", "query knowledge base", "记录一下", or similar intent to store or retrieve private knowledge.
Workflow Examples
A · User uploads files → auto-index ` User: "把这些文档加入知识库" Agent → save files to temp dir → kb_build(dir_path=tmp_dir, kb_name="my_kb") # returns immediately → "已开始后台构建，用 kb_status 检查进度" ` B · User dictates a note → insert ` User: "记住：STAR2000 低温写性能提升 8%" Agent → kb_note(text="STAR2000 低温写性能提升 8%", kb_name="my_kb", title="技术发现") → "已保存到知识库 my_kb" ` C · User asks a question → KB-assisted answer ` User: "NAND 筛选核心流程是什么？" Agent → context = kb_query("NAND 筛选核心流程", kb_name="my_kb") → append context to LLM prompt → generate answer ` D · Check if build finished before querying ` Agent → st = kb_status() → if st["status"] == "building": tell user to wait → else: proceed with kb_query(...) ` ---
py_mnn_kb — MNN Knowledge Base Skill
Local GraphRAG knowledge base backed by SQLite + MNN embeddings. Fully compatible with Android OfflineAI RAG database format. ---
1. Install dependencies
`bash pip install -r requirements.txt `
2. Configure
`bash cp config.example.json config.json
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster