Architecture
QMD (Query Markup Documents)
**QMD** is an on-device search engine created by Tobi Lutke (Shopify CEO) that indexes and searches markdown files, meeting transcripts, documentation, and knowledge bases using a hybrid approach comb
Key Features
- Fully local: Runs entirely on your machine using GGUF models via node-llama-cpp
- Hybrid search: Combines keyword (BM25), semantic (vectors), and LLM re-ranking
- MCP integration: Exposes an MCP server for Claude Desktop and Claude Code
- Zero API costs: All search operations run locally with no external API calls
Why It Matters
QMD represents a shift toward local-first AI tooling. Instead of sending documents to cloud APIs for retrieval, QMD provides high-quality search without latency or cost. This makes it ideal for AI agents that need fast, cheap document retrieval during autonomous workflows.
Resources
Build AI agents with Chipp
Create custom AI agents with knowledge, actions, and integrations—no coding required.
Learn more