Qmd

This gives Claude local search over your Markdown notes and docs with three modes: keyword (BM25), semantic vector search, and hybrid with reranking. Stick with the default keyword search, it's instant. Vector search works when keywords fail but can take a minute on cold start because it loads a local LLM for query expansion. Hybrid mode adds reranking on top and often times out, so skip it for interactive use. You index collections once with a glob pattern, then search or retrieve full documents by path or ID. The chunking handles messy Markdown fine, and there's cron examples for keeping the index fresh. Worth noting this searches your local files, not agent memory, so use both together.

skills.sh installs: 954
GitHub stars: 707
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add levineam/qmd-skill --skill qmd --agent claude-code

Installs into .claude/skills of the current project.

Files

qmd - Quick Markdown Search

Local search engine for Markdown notes, docs, and knowledge bases. Index once, search fast.

When to use (trigger phrases)

"search my notes / docs / knowledge base"
"find related notes"
"retrieve a markdown document from my collection"
"search local markdown files"

Default behavior (important)

Prefer qmd search (BM25). It's typically instant and should be the default.
Use qmd vsearch only when keyword search fails and you need semantic similarity (can be very slow on a cold start).
Avoid qmd query unless the user explicitly wants the highest quality hybrid results and can tolerate long runtimes/timeouts.

Prerequisites

Bun >= 1.0.0
macOS: brew install sqlite (SQLite extensions)
Ensure PATH includes: $HOME/.bun/bin

Install Bun (macOS): brew install oven-sh/bun/bun

Install

bun install -g https://github.com/tobi/qmd

Setup

qmd collection add /path/to/notes --name notes --mask "**/*.md"
qmd context add qmd://notes "Description of this collection"  # optional
qmd embed  # one-time to enable vector + hybrid search