qmd

Search local knowledge stores with hybrid BM25, vector, and LLM reranking.

Updated May 3, 2026

Search Tags:#search #mcp #local #knowledge-base #hybrid #qmd

Ready to run

npx skills add https://github.com/Yangel-hide/video-production-planner-agent --skill qmd-yangel-hide

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/Yangel-hide/video-production-planner-agent/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/Yangel-hide/video-production-planner-agent --skill qmd-yangel-hide

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local search across private knowledge stores, notes, docs, and transcripts without relying on cloud services, powered by a hybrid retrieval engine.

Core Features & Use Cases

Hybrid retrieval: BM25 keyword search, vector semantics, and LLM reranking on-device.
Local indexing and MCP integration: CLI access and Hermes Agent compatibility for automated workflows.
Use case: quickly locate meeting notes or project docs across large collections.

Quick Start

Install qmd, index your collections, and start searching your notes locally.

Frequently Asked Questions about qmd

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

FAQPage Schema

How does hybrid local search work for notes and documents?▼

Hybrid local search combines BM25 keyword matching, vector semantic retrieval, and LLM reranking to surface relevant notes and documents from local knowledge stores without relying on cloud services.

Can I search meeting transcripts and project docs locally without cloud services?▼

Yes, you can search meeting transcripts and project docs locally by indexing your collections on-device, enabling fast keyword lookup and semantic queries without sending data to external cloud servers.

Do I need MCP integration to search my local knowledge base?▼

MCP integration is required to expose search tools to Hermes Agent for automated workflows, though you can also perform local search directly via CLI access after indexing your collections.

What is the best way to set up semantic search for personal notes?▼

To set up semantic search for personal notes, install the search tool, index your local collections, and utilize the integrated BM25 and vector models to enable fast local retrieval and on-device reranking.

Why use LLM reranking for local document retrieval?▼

LLM reranking refines local document retrieval by reordering initial BM25 and vector search results on-device, ensuring the most contextually relevant notes and transcripts are surfaced accurately.