Search local text files with hybrid BM25, vector, and LLM reranking.
npx skills add https://github.com/CUexter/hermes-agent --skill qmd-cuexter
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/CUexter/hermes-agent/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/CUexter/hermes-agent --skill qmd-cuexter
Local, on-device search across personal knowledge bases, notes, transcripts, and documents using a hybrid retrieval engine that blends BM25 keyword matching, vector search, and LLM-powered reranking to deliver fast, private results without cloud dependencies.
Index your local notes with qmd and run a search using qmd query 'how to structure notes'.
High-intent search queries and answers about installing and using this skill.
Local note search uses a hybrid retrieval engine blending BM25 keyword matching, vector similarity, and LLM reranking to index markdown notes and transcripts on your device for offline, private results.
Hybrid search ranking combines BM25 keyword matching, vector similarity, and LLM reranking to retrieve relevant documents from personal knowledge bases, ensuring high-quality local search results without cloud dependencies.
You can run offline search queries on local documents via a CLI workflow, indexing markdown notes and text files on your device and querying directly through the command line for private retrieval.
Local indexing of personal notes and meeting transcripts requires Node.js version 22 or higher installed on your device to run the hybrid retrieval engine and manage local model operations.
Local search supports native MCP integration for Hermes Agent, enabling automated CLI workflows that query indexed markdown notes and documents using the hybrid retrieval engine.
The best way to retrieve meeting transcripts is using a local-first hybrid retrieval engine that blends BM25 and vector search with LLM reranking, indexing text files on your device for fast, private offline access.
GregsGreyCodeSearch local Markdown notes and transcripts with hybrid BM25, vector, and LLM reranking.
eddieluengSearch local markdown and text collections with hybrid retrieval and reranking.
jason660519Search local notes and transcripts with hybrid BM25, vector, and reranking retrieval.
nadicodeaiIndex and search local text collections with hybrid retrieval.
