qmd

Name: qmd
Availability: InStock
Author: zhouboyu-xreal

Index and search local markdown notes using BM25, vector search, and LLM reranking.

Updated Jun 9, 2026

Search Tags:#semantic search #local search #knowledge base #markdown notes #LLM reranking

Ready to run

npx skills add https://github.com/zhouboyu-xreal/Hermes-Memory --skill qmd-zhouboyu-xreal

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/zhouboyu-xreal/Hermes-Memory/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/zhouboyu-xreal/Hermes-Memory --skill qmd-zhouboyu-xreal

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires nodejs, sqlite, @tobilu/qmd, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies searching through vast collections of personal documents, notes, and meeting transcripts by providing a local, on-device search engine.

Core Features & Use Cases

Local Search Engine: Indexes markdown notes, meeting transcripts, and documentation without cloud dependencies.
Hybrid Search: Combines keyword matching, semantic understanding, and LLM reranking for accurate results.
CLI and MCP Integration: Supports CLI commands and can be integrated with the Hermes Agent's MCP.

Quick Start

Run the 'qmd search "my keyword"' command to search for 'my keyword' in your local knowledge base.

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 locally without sending data to the cloud?▼

To search markdown notes locally without cloud dependencies, you can use an on-device search engine that indexes personal documentation and meeting transcripts directly on your machine.

What is hybrid search with LLM reranking for personal knowledge bases?▼

Hybrid search with LLM reranking combines traditional keyword matching and semantic vector understanding, then uses a large language model to reorder results for higher accuracy in a local knowledge base.

Can I run a semantic search on meeting transcripts using command-line tools?▼

Yes, you can run semantic search on meeting transcripts using command-line tools by executing a search command like 'qmd search' after indexing your local knowledge base.

Do I need Node.js and SQLite to set up a local markdown search engine?▼

Yes, you need Node.js and SQLite to set up this local markdown search engine, as it requires the Node.js runtime, SQLite database, and the @tobilu/qmd package for on-device indexing.

What's the best way to integrate local document search with an automated agent?▼

The best way to integrate local document search with an automated agent is using MCP integration, which allows automated searches of your indexed markdown notes without manual CLI input.

Does on-device vector search work for large collections of personal documentation?▼

On-device vector search works for large collections of personal documentation by utilizing local SQLite indexing to manage notes and transcripts efficiently without requiring external cloud services.