qmd
Installation
Summary
Local keyword and semantic search for indexed Markdown collections with three search modes.
- Supports three search modes:
qmd search(fast BM25 keyword matching, typically instant),qmd vsearch(semantic similarity via local embeddings, slower), andqmd query(hybrid with LLM reranking, generally slowest) - Index Markdown collections once with
qmd collection add, then search across multiple files or retrieve specific documents by path or ID - Includes maintenance commands (
qmd update,qmd embed) to keep indexes fresh; keyword search updates are fast, but semantic embeddings can be slow on first run - Distinguishes from agent memory search:
qmdqueries your local files on disk, while memory search accesses saved facts from prior interactions
SKILL.md
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 vsearchonly when keyword search fails and you need semantic similarity (can be very slow on a cold start). - Avoid
qmd queryunless the user explicitly wants the highest quality hybrid results and can tolerate long runtimes/timeouts.