qmd

Search local knowledge bases with hybrid keyword and semantic queries.

Updated May 11, 2026

Search Tags:#local search #knowledge base #search engine #document search #text retrieval

Ready to run

npx skills add https://github.com/richardnguyen0715/keep-it-real --skill qmd-richardnguyen0715

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/richardnguyen0715/keep-it-real/tree/main/refer-projects/hermes-agent/optional-skills/research/qmd
Command: npx skills add https://github.com/richardnguyen0715/keep-it-real --skill qmd-richardnguyen0715

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, sqlite, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of searching through vast collections of notes, documentation, and meeting transcripts locally and efficiently.

Core Features & Use Cases

Hybrid Search: Combines keyword matching, semantic understanding, and LLM reranking for local document search.
CLI & MCP Integration: Provides a command-line interface and can integrate with other systems via the Management Console Protocol (MCP).
Use Case: For users who need to quickly search their personal knowledge base across various markdown and text files, without relying on cloud services.

Quick Start

Add a collection and start searching with qmd search "query".

Frequently Asked Questions about qmd

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

FAQPage Schema

How do I search my personal knowledge base locally without relying on cloud services?▼

You can search your personal knowledge base locally by using a hybrid search engine that combines keyword matching, semantic understanding, and LLM reranking across markdown and text files. This runs entirely on-device without cloud services.

Do I need Node.js and SQLite to perform local text retrieval on my notes?▼

Yes, local text retrieval for your notes requires Node.js and SQLite. These dependencies enable the on-device search engine to index and query your personal knowledge base efficiently.

How does hybrid search work for finding information in meeting transcripts?▼

Hybrid search for meeting transcripts works by combining BM25 keyword matching, vector semantic search, and LLM reranking. This approach ensures high-relevance results from your local document collections.

Can I integrate local document search with other systems via a command-line interface?▼

Yes, you can integrate local document search with other systems using the provided command-line interface and Management Console Protocol (MCP). This allows seamless connection with agents like Hermes.

What is the best way to add a collection and search markdown files on my device?▼

The best way to search markdown files on your device is to add your collection to the local search engine and execute a query using the command line. The system handles indexing and retrieval automatically.

Are there limitations to using an on-device search engine for large document collections?▼

Limitations of an on-device search engine include dependency on local hardware resources for indexing and querying large document collections. Performance depends entirely on your device's storage and processing capabilities.