+18
日增长
+293
周增长
+700
月增长
31,142
stars
1,953
forks
106
watchers
653
prs
465
issues
14
releases
README
QMD - Query Markup Documents An on-device search engine for everything you need to remember. Index your markdown notes, meeting transcripts, documentation, and knowledge bases. Search with keywords or natural language. Ideal for your agentic flows. QMD combines BM25 full-text search, vector semantic search, and LLM re-ranking—all running locally via node-llama-cpp with GGUF models. mermaid flowchart LR Q[User Query] -- X[Query Expansion] Q -- FTS[BM25 Search] Q -- VS[Vector Search] X -- HYDE[HyDE] X -- VEC[Vec dense sentences] X -- LEX[Lex BM25 keywords] HYDE -- VS VEC -- VS LEX -- FTS VS -- RRF[Reciprocal Rank Fusion] FTS -- RRF RRF -- RR[LLM Reranker] RR -- OUT[Final ranked results] Typed expansions are routed exclusively: lex → BM25/FTS, vec and hyde → vector search. The original query is sent to both backends, then fused with RRF and reranked. You can read more about QMD's progress in the CHANGELOG. Quick Start sh Install globally (Node or Bun) npm install -g @tobilu/qmd or bun install -g @tobilu/qmd Or run directly npx @tobilu/qmd ... bunx @tobilu/qmd ... Create collections for your notes, docs, and meeting transcripts qmd collection add ~/notes --name notes qmd collection add ~/Documents/meetings --name meetings qmd collection add ~/work/docs --name docs Add context to help with search results, each piece of context will be returned when matching sub documents are returned. This works as a tree. This is the key feature of QMD as it allows LLMs to make much better contextual choices when selecting documents. Don't sleep on it! qmd context add qmd://notes "Personal notes and ideas" qmd context add qmd://meetings "Meeting transcripts and notes" qmd context add qmd://docs "Work documentation" Generate embeddings for semantic search qmd embed Search across everything qmd search "project timeline" Fast keyword search qmd vsearch "how to deploy" Semantic search qmd query "quarterly planning process" Hybrid + reranking (best quality) Get a specific document qmd get "meetings/2024-01-15.md" Get a document by docid (shown in search results) qmd get "abc123" Get multiple documents by glob pattern qmd multi-get "journals/2025-05.md" Search within a specific collection qmd search "API" -c notes Export all matches for an agent qmd search "API" --all --files --min-score 0.3 Using with AI Agents QMD's --json and --files output formats are designed for agentic workflows: sh Get structured results for an LLM qmd search "authentication" --json -n 10 List all relevant files above a threshold qmd query "error handling" --all --files --min-score 0.4 Retrieve full document content qmd get "docs/api-reference.md" --full MCP Server Although the tool works perfectly fine when you just tell your agent to use it on the command line, it also exposes an MCP (Model Context Protocol) server for tighter integration. Tools exposed: - query — Search with typed sub-queries (lex/v
Top issues
#952vsearch takes ~70 s on an 11k-vector collection: exact scan runs per expanded query, expansions not deduplicated9 comments · 2026-09-14#897Embedding inputs at/over the context's physical batch boundary (512 tokens) silently store deterministic garbage vectors7 comments · 2026-08-15#717Lossy path normalization breaks QMD_EDITOR_URI for files with spaces4 comments · 2026-06-08#735qmd embed deadlocks at 0% CPU on Apple M5 Max + macOS 26.4 — Metal shader JIT compile failure in bundled llama.cpp b8390 (distinct from #673/#724)5 comments · 2026-06-14#724qmd embed cannot complete large collections in one run — session maxDuration (10 min) aborts mid-run with mass "LLM session expired before embedding chunk" failures2 comments · 2026-06-11#685Return multiple results per file3 comments · 2026-05-25#679qmd embed hangs indefinitely on "Gathering information" on Windows2 comments · 2026-05-25#971stdio MCP server: `status` racing a model-loading `query` never answers on stdout3 comments · 2026-09-20
Latest release
v2.8.3 v2.8.3 2026-08-16[2.8.3] - 2026-08-16 Security - qmd update no longer runs a project-local .qmd/index.yml's update: commands without approval (886). That file arrives with a git clone and is adopted automatically for any command run inside the tree, so cloning a repository and running qmd update executed shell commands chosen by whoever wrote it. On a terminal QMD now lists the commands and asks; with nobody to ask it skips them and keeps indexing. Approvals are recorded per config file and per command set in /trusted.json, so editing a command — or a git pull that rewrites one — asks again. N
相关报道 (4)
News & coverage (6)
Hacker NewsQMD - Quick Markdown Search▲ 25 · 7 comments · 2026-01-20korbenQMD - A local search engine for your Markdown notes2026-03-23noteGetting Started with Local AI Search using qmd — From Hybrid Search Mechanisms to Claude Code Integration2026-01-30HackerNoonHow I Built a Self-Maintaining Knowledge Base for 6 Projects Using Claude Code & Karpathy's LLM Wiki2026-04-20MarkTechPostAndrej Karpathy Open-Sources ‘Autoresearch’: A 630-Line Python Tool Letting AI Agents Run Autonomous ML Experiments on Single GPUs2026-03-08InfoWorldCreate a free data dictionary with R2023-04-27