qmd

Index and search local knowledge bases with hybrid retrieval via CLI and MCP.

Updated Jun 17, 2026
One-click install
npx skills add https://github.com/anilcan-kara/nozich-agent --skill qmd-anilcan-kara
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/anilcan-kara/nozich-agent/tree/main/optional-skills/research/qmd
Command: npx skills add https://github.com/anilcan-kara/nozich-agent --skill qmd-anilcan-kara

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Indexes and searches personal knowledge bases, notes, documents, and transcripts locally using a hybrid retrieval engine that combines BM25, vector search, and LLM reranking, with no cloud dependency.

Core Features & Use Cases

  • Local indexing of markdown notes, meeting transcripts, and documents for fast retrieval.
  • Hybrid search that blends keyword matching, semantic understanding, and reranking for high-quality results.
  • CLI and MCP integration to automate and embed search capabilities into workflows.

Quick Start

Install qmd, index your collections, and run a query locally to see results.

Frequently Asked Questions about qmd

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

FAQPage Schema
How do I search notes and transcripts locally without cloud dependency?

Local on-device search for notes and transcripts is facilitated by indexing collections with a hybrid retrieval engine. The engine combines BM25, vector search, and LLM reranking to provide fast keyword and semantic results without any cloud dependency.

Can I use local search for markdown notes and meeting transcripts on macOS and Linux?

Yes, local search for markdown notes and meeting transcripts is fully supported on macOS and Linux environments. The tool integrates via a CLI and MCP, allowing you to index documents and execute queries directly within these operating systems.

What is hybrid retrieval and how does it improve personal knowledge base search?

Hybrid retrieval improves personal knowledge base search by blending keyword matching, semantic understanding, and LLM reranking. This combination ensures high-quality results that capture both exact term matches and contextual meaning from indexed documents and transcripts.

How do I integrate local document search into my existing workflows via MCP?

You can integrate local document search into existing workflows via MCP and CLI compatibility. After indexing your markdown notes and transcripts, the MCP integration allows you to embed search capabilities directly into automated processes and external applications.

Does local on-device search support semantic search and reranking for large document collections?

Yes, local on-device search supports semantic search and LLM reranking for indexed document collections. The hybrid search pipeline processes large personal knowledge bases by reranking vector and BM25 results locally, ensuring accurate retrieval without cloud processing.