Skip to content

[GitHub Trending] tobi/qmd

7.8 relevance
Score Breakdown
technical depth
6
novelty
7
actionability
8
community
7
strategic
6
personal
7

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

Local CLI search engine is a practical developer tool for privacy-focused knowledge management.

2026-04-06 devtools GitHub Trending
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local - tobi/qmd
Summary

QMD is an open-source on-device search engine that indexes markdown and documents using BM25, vector embeddings, and LLM reranking via node-llama-cpp with GGUF models. It exposes an MCP server with HTTP transport for agent integration, supporting hybrid queries and context hierarchies to improve retrieval for AI workflows.

Key Takeaway

Deploy QMD's MCP HTTP daemon to provide persistent, cached model inference for efficient context retrieval in your AI agent workflows.

Why it matters

For your focus on agent orchestration, QMD provides a local, privacy-preserving alternative to cloud-based retrieval, reducing latency and cost while enhancing context-aware document selection in multi-agent systems.