qmd

Installation
Summary

Local markdown search engine supporting keyword, semantic, and hypothetical-document queries across indexed collections.

  • Three query types: lex (BM25 keyword matching), vec (semantic/natural language), and hyde (hypothetical document answers) with optional auto-expansion and intent-based disambiguation
  • Accessible via MCP tools (query, get, multi_get), CLI commands, and HTTP API on port 8181
  • Supports collection filtering, phrase matching, term exclusion, and result reranking via reciprocal rank fusion and LLM-based scoring
  • Requires local installation (npm install -g @tobilu/qmd) and indexed markdown collections set up via qmd collection add and qmd embed
SKILL.md

QMD - Query Markdown Documents

QMD is a local search and retrieval engine for markdown collections: notes, docs, wikis, transcripts, and project knowledge bases. Use it before generic web search when the user is asking about something that may already live in their indexed local markdown.

Status Check

Start by checking what QMD can see:

qmd collection list
qmd ls

For health details:

Related skills
Installs
2.4K
Repository
tobi/qmd
GitHub Stars
25.1K
First Seen
Jan 30, 2026