使用 QMD 在本地笔记、文档和会议记录中搜索代理上下文
Index local notes, docs, and meeting transcripts, then return ranked files or structured JSON so an agent can pull only the context it needs.
Prerequisites
Node or Bun, local document folders, optional local GGUF model via node-llama-cpp for semantic search and reranking
Installation
Use the upstream install or setup path that matches your environment:
- npm install -g @tobilu/qmd
- npx @tobilu/qmd ...
- npm install @tobilu/qmd
- brew install sqlite
Requirements and caveats from upstream:
- QMD combines BM25 full-text search, vector semantic search, and LLM re-ranking—all running locally via node-llama-cpp with GGUF models.
- Use QMD as a library in your own Node.js or Bun applications.
- The SDK requires explicit dbPath — no defaults are assumed. This makes it safe to embed in any application without side effects.
Basic usage or getting-started notes:
- sh
- # or
- bun install -g @tobilu/qmd
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/tobi/qmd/HEAD/README.md
Documentation
- https://github.com/1991513ccie-png/skills
