tobi/qmd

Health v2 · maintenance only

Adoption not part of the score

29259 stars · 1823 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

QMD is a local, on-device CLI search engine that indexes markdown notes, docs, meeting transcripts, and knowledge bases. It combines BM25 full-text search, vector semantic search, and LLM re-ranking (via node-llama-cpp with GGUF models) with reciprocal rank fusion, and exposes an MCP server for AI agent workflows.

Use cases

• search my local markdown notes from the terminal
• build a local search engine for my docs and meeting notes
• semantic search over my knowledge base without the cloud
• give my AI agent a tool to search my files
• hybrid keyword and vector search with reranking
• index meeting transcripts and query them in natural language

When to choose

• you want fully local, private search over personal docs and notes
• you need JSON/file-list output designed for agentic and MCP workflows
• you want SOTA hybrid retrieval (BM25 + vectors + HyDE + LLM reranking) on-device

When to avoid

• you need to index large shared team wikis with multi-user access
• you want a hosted or web-based search service with a GUI
• you lack hardware for local GGUF model inference

Facets

cli-tool · maturity active

search-engine rag llm-inference cli mcp developer-tools large-language-models cli bun cross-platform windows local-search bm25 vector-search embeddings hybrid-search reranking hyde gguf on-device knowledge-base agentic-workflows markdown search retrieval-augmented-generation command-line nodejs macos linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tobi/qmd")