qmd

Search local knowledge bases with hybrid BM25, vector, and reranking retrieval.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local, on-device search for personal knowledge bases, notes, docs, and meeting transcripts using a hybrid retrieval engine that combines BM25, vector search, and LLM reranking to deliver relevant results without cloud dependencies.

Core Features & Use Cases

  • Hybrid retrieval: BM25, vector search, and LLM reranking work together to surface relevant results across notes, docs, and transcripts.
  • Local execution: runs entirely on your machine (macOS/Linux) with no data leaving your device.
  • MCP integration: exposes tools to Hermes Agent via MCP for seamless automation and chaining with other skills.
  • Use Case: quickly locate a meeting decision or a specific snippet from a research doc across large collections.

Quick Start

Query your local notes with a simple keyword, for example 'qmd search onboarding'.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I search local notes and transcripts offline?

Search local notes and transcripts offline using a hybrid retrieval engine combining BM25, vector search, and LLM reranking. It runs entirely on your machine with no cloud dependencies, ensuring your personal knowledge base data never leaves your device.

What is hybrid retrieval for personal knowledge management?

Hybrid retrieval for personal knowledge management combines BM25 keyword matching, vector search, and LLM reranking to surface relevant results. This approach delivers fast, accurate retrieval across large collections of local notes, docs, and meeting transcripts.

Can I use this hybrid search engine with Hermes automation?

You can use this hybrid search engine with Hermes automation via MCP integration. It exposes tools to the Hermes Agent, enabling seamless automation and chaining with other skills for local knowledge base retrieval tasks.

Does local vector search work on macOS and Linux without cloud dependencies?

Local vector search works on macOS and Linux without cloud dependencies. The hybrid retrieval engine runs entirely on-device, requiring no cloud connectivity to perform BM25, vector search, and LLM reranking across your local docs.

What's the best way to find meeting decisions across large document collections?

The best way to find meeting decisions across large document collections is using a local hybrid retrieval engine. By combining BM25, vector search, and LLM reranking, you can quickly locate specific snippets or decisions from research docs and meeting transcripts.