qmd

Search local notes and transcripts with hybrid BM25 and vector retrieval.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/attentiondotnet/hermes-agent --skill qmd-attentiondotnet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/attentiondotnet/hermes-agent/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/attentiondotnet/hermes-agent --skill qmd-attentiondotnet

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Index and search personal knowledge bases, notes, docs, and meeting transcripts locally using a hybrid retrieval engine that combines BM25, vector search, and LLM-based reranking.

Core Features & Use Cases

  • Local, on-device search across markdown/text documents and transcripts
  • Hybrid retrieval combining keyword matching, semantic search, and reranking for high-quality results
  • CLI and MCP integration to connect Hermes Agent without cloud dependencies

Quick Start

Index a local notes folder with qmd, then run a hybrid search for your query.

Frequently Asked Questions about qmd

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search personal notes and meeting transcripts offline without cloud dependencies?

You can search personal notes and meeting transcripts offline by indexing local folders with a hybrid retrieval engine that runs entirely on-device, eliminating cloud dependencies while querying markdown, text, and transcript files.

What is hybrid retrieval and how does it improve local knowledge base search?

Hybrid retrieval improves local knowledge base search by combining BM25 keyword matching, vector semantic search, and LLM-based reranking to deliver higher quality results than any single search method. It processes your query locally for precise document ranking.

Can I use hybrid search with Hermes Agent through MCP integration?

Yes, you can connect hybrid search to Hermes Agent through MCP integration and CLI commands. This allows the agent to query your local knowledge base directly without relying on external cloud services or remote API calls.

What's the best way to index local markdown and text documents for vector search?

The best way to index local markdown and text documents for vector search is using a local hybrid retrieval engine that supports BM25 and semantic search natively. Index your notes folder, then execute hybrid queries combining keyword and vector matching.

Does LLM reranking work for offline document search without internet access?

LLM reranking enhances offline document search results by refining initial BM25 and vector search outputs. The hybrid retrieval engine operates locally to process and rerank your personal knowledge base queries without requiring continuous internet connectivity.