Qmd

Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.

Peter Steinberger

@steipete

What This Skill Does

Command-line tool for indexing local files and searching them with BM25, vector, or hybrid retrieval, plus optional reranking. Supports MCP mode for integration with AI agents.

Replaces building custom local search pipelines by providing a single CLI that combines BM25, vector embeddings, and reranking with minimal setup.

When to Use It

  • Index a directory of markdown files for fast local search
  • Search local documentation using BM25 keyword matching
  • Find semantically similar documents with vector search
  • Run hybrid search combining keyword and semantic results
  • Retrieve a specific document snippet by path and line number
  • Expose indexed files to an AI agent via MCP mode

Install

$ openclaw skills install @steipete/qmd

qmd

Use qmd to index local files and search them.

Indexing

  • Add collection: qmd collection add /path --name docs --mask "**/*.md"
  • Update index: qmd update
  • Status: qmd status

Search

  • BM25: qmd search "query"
  • Vector: qmd vsearch "query"
  • Hybrid: qmd query "query"
  • Get doc: qmd get docs/path.md:10 -l 40

Notes

  • Embeddings/rerank use Ollama at OLLAMA_URL (default http://localhost:11434).
  • Index lives under ~/.cache/qmd by default.
  • MCP mode: qmd mcp.

Top skills in this category