qmd
Local doc search engine with BM25 + vectors + LLM re-ranking — by Shopify's CEO
Expert verdict
Skip
2-2The Panel's Take
qmd is a lightweight local search engine built by Tobi Luetke, CEO of Shopify, for indexing and querying personal knowledge bases, documentation, and meeting notes — entirely offline. It combines three retrieval approaches in a single pipeline: BM25 full-text search for exact keyword matches, vector semantic search via ONNX-based embeddings, and LLM re-ranking using GGUF models through node-llama-cpp. All three stages run locally with no cloud dependency. The tool ships in multiple deployment modes: a CLI for ad-hoc queries, a Node.js library for programmatic use, an HTTP service for local API access, and — most useful for AI workflows — a native MCP server that lets Claude Code, Cursor, and similar editors query your local knowledge base directly during coding sessions. The hybrid retrieval approach means it handles both "find the exact error message from last week's standup notes" and "what was our decision about the auth architecture" equally well. What makes this notable beyond its technical approach is provenance: Luetke shipped it as a personal tool he actually uses, not a startup product. The GitHub history shows active iteration and he's been talking about it on X. It's a credible signal of where pragmatic AI-augmented knowledge management is heading for technical users who prefer local-first tools.
Share this verdict
qmd verdict: SKIP ⏭️ 2 ships · 2 skips from the expert panel Full review: shiporskip.io/tool/qmd-tobi-luetke-local-doc-search-rag-mcp-bm25-vector
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Similar Products
Compare qmd with Others
Looking for qmd alternatives?
Compare qmd with every other Developer Tools tool reviewed by our panel.
See all Developer Tools alternativesEmbed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/qmd-tobi-luetke-local-doc-search-rag-mcp-bm25-vector" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/qmd-tobi-luetke-local-doc-search-rag-mcp-bm25-vector" alt="qmd Skip verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/qmd-tobi-luetke-local-doc-search-rag-mcp-bm25-vector)<iframe src="https://shiporskip.io/embed/qmd-tobi-luetke-local-doc-search-rag-mcp-bm25-vector" title="qmd ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“Hybrid BM25 + vector + LLM re-rank is the right architecture for personal knowledge search — each layer catches what the others miss. The MCP server mode is genuinely useful: being able to ask Claude Code 'what did we decide about X last month' against my own notes changes the workflow. MIT licensed and from someone who ships real products.”
“This is a well-executed weekend project, not a production tool. It requires GGUF models and manual embedding setup — a meaningful friction barrier for non-technical users. The 'built by a CEO' narrative drives GitHub stars more than the technical differentiation. Obsidian with a local AI plugin gets you here with better UX.”
“The pattern here — local hybrid retrieval as an MCP server feeding into AI coding agents — will be ubiquitous in two years. Today it's a technical power-user tool; tomorrow it's how everyone's AI assistant knows the institutional context behind the code. qmd is an early, clean implementation of that pattern.”
“I manage a lot of notes, references, and creative briefs, but the setup friction here — GGUF models, CLI configuration — makes this inaccessible for most creators. The concept is great; the UX needs a front-end before it reaches beyond developers.”