qmd

Name: qmd
Availability: InStock
Author: samuelmukoti

Index markdown notes and transcripts with BM25, vector search, and LLM reranking.

Updated Apr 21, 2026

Search Tags:#markdown #search #local #knowledge-base #vector-search #hybrid-search

Ready to run

npx skills add https://github.com/samuelmukoti/myai-agent --skill qmd-samuelmukoti

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/samuelmukoti/myai-agent/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/samuelmukoti/myai-agent --skill qmd-samuelmukoti

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local, on-device search across markdown notes, docs, and transcripts using a hybrid retrieval engine that combines BM25, vector search, and LLM reranking for fast, private results.

Core Features & Use Cases

Hybrid retrieval: BM25 keyword matching, semantic vector search, and LLM-based reranking for high-quality results.
Local-first workflow: Indexes notes and transcripts on-device, with MCP integration for external tooling.
Use Case: Personal knowledge management, research, and team documentation search across local collections.

Quick Start

Ask qmd to search your local notes, docs, and meeting transcripts for a topic and review the top results.

Frequently Asked Questions about qmd

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

FAQPage Schema

How do I search markdown notes and meeting transcripts locally on my device?▼

You can search markdown notes and meeting transcripts locally by indexing them on-device with a hybrid engine that combines BM25 keyword matching, semantic vector search, and LLM reranking for fast, private results.

What is hybrid retrieval for personal knowledge bases?▼

Hybrid retrieval for personal knowledge bases combines BM25 keyword matching, semantic vector search, and LLM-based reranking to deliver high-quality search results across local collections of notes and documents.

Does local vector search work without sending my docs to the cloud?▼

Yes, local vector search works entirely on-device. It indexes your notes, docs, and transcripts locally, ensuring fast, private queries without sending your personal knowledge base to external servers.

Can I use MCP integration to search my local documentation?▼

Yes, you can use MCP integration to search local documentation. The engine operates in MCP stdio or HTTP daemon modes, supporting warm models and allowing external tooling to query your local collections.

Do I need Node.js and SQLite to run a local knowledge base search?▼

Yes, running a local knowledge base search requires Node.js >= 22 and SQLite with extension support, specifically needed for macOS environments to index files and execute private queries.

What is the best way to search exported contexts across local collections?▼

The best way to search exported contexts across local collections is using a hybrid retrieval engine that merges BM25, vector search, and LLM reranking, providing fast and private results via CLI or MCP integration.