← Back to Skills Marketplace
145
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install py-mnn-kb
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...
Usage Guidance
This skill appears to do what it says: build and query a local MNN-based KB and (optionally) call an LLM for answers. Before installing, consider: 1) Model download: the first run auto-downloads a ~400MB embedding model from ModelScope (modelscope.cn) into the repo's assets directory — run this on a machine and network where you are comfortable downloading large binary files. 2) Secrets: the tool expects an API key in config.json for LLM generation; that file is written to disk (it is gitignored by the project). Do not put highly sensitive keys there unless you control the environment. 3) Data exfiltration: if you enable the LLM generation path (default examples show this), retrieved KB context and queries will be sent to the configured OpenAI-compatible endpoint. Use --no-llm or point to a trusted/local LLM if you need to keep KB content local. 4) Review code if you have high security needs: the model download and llm invocation are visible in scripts/py_mnn_kb.py (no obfuscated endpoints or hidden backdoors were detected). 5) Run in an isolated environment (virtualenv / container) and inspect config.json and the repo before giving it access to private documents.
Capability Analysis
Type: OpenClaw Skill
Name: py-mnn-kb
Version: 1.0.0
The skill implements a sophisticated local GraphRAG knowledge base using MNN embeddings and SQLite, supporting vector search, BM25, and entity relationship mapping. It includes automated model downloading from ModelScope and background indexing for various document formats (PDF, Word, Excel, etc.) via subprocess management in `scripts/py_mnn_kb.py`. While the skill performs high-risk actions like recursive file system access and background process execution, these behaviors are explicitly documented and strictly aligned with the stated purpose of a local knowledge base, with no evidence of malicious intent, data exfiltration, or obfuscation.
Capability Assessment
Purpose & Capability
Name/description (local MNN KB, GraphRAG) match the delivered artifacts: a Python implementation, CLI, and instructions for building/querying a local KB. Required components (MNN embedding backend, text parsers, optional LLM client) are appropriate for the stated functionality.
Instruction Scope
SKILL.md/README instruct the agent to index local files, insert notes, and return retrieved context. The README and code also permit using an LLM for generation (configurable via config.json / --no-llm). This means retrieved private context may be sent to a remote OpenAI-compatible endpoint if you enable LLM answering — a normal feature for RAG but an important privacy consideration. There is a small inconsistency: SKILL.md explicitly states 'no LLM call is made inside this tool' for kb_query, yet other docs and config include an llm_api section and examples that perform LLM generation. Confirm desired behavior (use --no-llm if you want pure local retrieval).
Install Mechanism
No formal install spec in registry (instruction-only), but code auto-downloads an embedding model (~400 MB) from ModelScope (modelscope.cn) on first run via urllib.request. Downloading from ModelScope is expected for an embedding backend; this does write model files to disk. The skill asks you to pip install requirements.txt (standard).
Credentials
The skill does not require platform environment variables, but it expects a local config.json with an llm_api.api_key and base_url if you want LLM generation. Storing the API key in config.json (gitignored by the project) is consistent but means a secret is kept on disk. The presence of openai (or OpenAI-compatible) client is justified by the optional LLM step; however, enabling it will send KB context and user queries to whatever endpoint you configure. If you do not want outbound data leakage, use --no-llm or provide a local LLM endpoint you trust.
Persistence & Privilege
always:false and the skill does not request force-inclusion or system-wide config changes. It writes its own artifacts (assets/, knowledge_bases/, downloaded model) in its directory and updates the model's llm_config.json for embedding tokenization alignment — expected for this use case. It does not modify other skills or system-wide agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install py-mnn-kb - After installation, invoke the skill by name or use
/py-mnn-kb - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
initial publish
Metadata
Frequently Asked Questions
What is MNN Local Knowledge Base?
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... It is an AI Agent Skill for Claude Code / OpenClaw, with 145 downloads so far.
How do I install MNN Local Knowledge Base?
Run "/install py-mnn-kb" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is MNN Local Knowledge Base free?
Yes, MNN Local Knowledge Base is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does MNN Local Knowledge Base support?
MNN Local Knowledge Base is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created MNN Local Knowledge Base?
It is built and maintained by er6y (@er6y); the current version is v1.0.0.
More Skills