Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
npx skills add https://github.com/JuanMS20/solviora-agent --skill qmd-juanms20
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/JuanMS20/solviora-agent/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/JuanMS20/solviora-agent --skill qmd-juanms20
Local, on-device search enables fast, private retrieval across notes, transcripts, and documents without relying on cloud services.
Install qmd globally, add a collection with qmd collection add <path> --name <name>, then run qmd to start indexing and searching.
High-intent search queries and answers about installing and using this skill.
qmd enables local, on-device search across Markdown notes and transcripts by indexing file collections and running BM25, vector, and LLM reranking retrieval without cloud dependencies. It requires Node.js 22 or newer and local SQLite with extension support on macOS.
Hybrid retrieval for local document search combines BM25 keyword matching, vector-based semantic search, and LLM reranking to deliver high-quality results from indexed Markdown and text files. This multi-layer approach captures both exact terms and contextual meaning without cloud dependencies.
Yes, on-device note search requires Node.js 22 or newer and local SQLite with extension support on macOS. These dependencies enable the local embedding, indexing, and hybrid retrieval pipeline for your Markdown and text file collections.
Yes, qmd supports MCP integration to expose search tools to Hermes Agent while maintaining a locally-driven workflow. This allows AI agents to query your indexed Markdown notes and transcripts without sending data to cloud services.
Install qmd globally, add a collection using the command qmd collection add <path> --name <name>, then run qmd to start indexing and searching. This prepares your local Markdown and text files for hybrid retrieval queries.
Local note search on macOS requires local SQLite with extension support and Node.js 22 or newer. Without these specific environment configurations, the qmd CLI cannot manage collections, generate embeddings, or perform hybrid retrieval.
thisismynewfmail-uiSearch local markdown notes and transcripts with hybrid retrieval.
steipeteIndex local files and search them with BM25, vector, and hybrid queries.
afel6Search local markdown and meeting transcripts with hybrid BM25, vector, and reranking retrieval.
sheawinklerSearch local markdown and text collections using hybrid BM25 and vector ranking.
