QMD — локальный поиск по заметкам и документам

★ 28.9K

QMD (Query Markup Documents) is a local search engine over your text materials: it indexes markdown notes, meeting transcripts, documentation, and knowledge bases and lets you search them with keywords and natural language. Reach for it when you need to quickly find things in your pile of notes and documents, including as a tool for agentic flows: pose a query in words and get relevant fragments. It combines BM25 full-text search, vector semantic search, and LLM re-ranking — all running locally via node-llama-cpp with GGUF models, no cloud. Its focus is local hybrid search (keywords + meaning + LLM rerank) over personal documents, including for agents, not a cloud service or a full RAG platform with chat: the value is private, accurate search over your own materials right on the device. It suits people who want to search their notes and wire that search into their own AI agents.