Search local markdown notes and transcripts with hybrid BM25 and vector retrieval.
npx skills add https://github.com/adm-humanerd/drewgent --skill qmd-adm-humanerd
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/adm-humanerd/drewgent/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/adm-humanerd/drewgent --skill qmd-adm-humanerd
Indexes and searches personal knowledge bases locally, combining keyword matching, semantic understanding, and LLM-powered reranking to deliver fast, relevant results without cloud dependencies.
Run a hybrid local search over your knowledge base using qmd to retrieve relevant notes and transcripts.
High-intent search queries and answers about installing and using this skill.
Hybrid retrieval merges BM25 keyword matching with vector search and LLM reranking to index and search local markdown notes, transcripts, and documentation on-device. It uses an MCP interface to expose search tools without cloud dependencies.
Yes, you can search personal markdown notes and transcripts offline using a local-first hybrid retrieval engine. It runs entirely on-device with local models, ensuring no cloud dependencies are required to retrieve relevant results from your knowledge base.
Setting up local search for markdown notes requires an on-device environment with local models configured. You use the MCP interface to expose native search tools, enabling the Drewgent Agent to automate retrieval workflows over your personal knowledge base.
Yes, local knowledge search works with the Drewgent Agent via MCP integration. It exposes native search tools through the MCP interface, enabling seamless automation and workflow integration for retrieving indexed notes and transcripts on-device.
The best way to search project documentation without cloud dependencies is using a local-first hybrid retrieval engine. It combines BM25 keyword search, vector search, and LLM reranking to deliver fast, relevant results entirely on-device.
Yes, you need local models to run BM25 and vector search on personal knowledge bases. The hybrid retrieval engine requires an on-device setup to perform indexing and LLM reranking, ensuring the process remains local-first with no cloud dependencies.
ChimeraFoundationaIndex local markdown notes, transcripts, and docs for hybrid on-device search.
dy9759Convert URLs, documents, images, and text into structured notes saved to WPS Notes.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
Yangel-hideSearch local knowledge stores with hybrid BM25, vector, and LLM reranking.
