qmd

Index local knowledge bases and search notes with hybrid retrieval.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/zulumonkeymetallic/bob --skill qmd-zulumonkeymetallic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/zulumonkeymetallic/bob/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/zulumonkeymetallic/bob --skill qmd-zulumonkeymetallic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local, on-device search for personal knowledge bases, notes, docs, and meeting transcripts, delivering fast, private retrieval without cloud dependencies.

Core Features & Use Cases

  • Local on-device indexing and search across Markdown notes, documents, and transcripts.
  • Hybrid retrieval combining BM25 keyword search, vector semantic search, and LLM-based reranking for high-quality results.
  • CLI-driven workflows with optional MCP integration to connect Hermes Agent to external tooling.
  • Use cases include personal knowledge management, academic research notes, and organizing project documentation, all without sending data to the cloud.

Quick Start

Install qmd and index your documents locally, then run a query to locate relevant notes.

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 transcripts locally without cloud dependencies?

Local hybrid search indexes personal knowledge bases on-device, enabling fast retrieval across notes and transcripts without cloud dependencies. It combines BM25 keyword search, vector semantic search, and LLM reranking to deliver private results.

What is hybrid retrieval and how does it work for personal knowledge management?

Hybrid retrieval combines BM25 keyword search with vector semantic search and LLM-based reranking. This mechanism ensures high-quality results when querying personal knowledge management systems, academic research notes, or meeting transcripts across multiple collections.

Do I need Node.js to run local knowledge base indexing?

Yes, local knowledge base indexing requires a local runtime like a Node.js environment. You need the ability to run the QMD CLI to index documents locally and execute queries to locate relevant notes.

Can I use MCP integration to connect local search with external tooling?

Yes, local search supports optional MCP integration to connect your indexed knowledge base to external tooling. This allows CLI-driven workflows to extend retrieval capabilities into broader agent-based ecosystems.

What is the best way to organize and search academic research notes on my own device?

The best way to search academic research notes locally is using a hybrid retrieval system that indexes Markdown notes and documents on-device. It applies BM25, vector search, and LLM reranking across multiple collections for high-quality results.