Index local markdown collections for hybrid BM25 and vector search.
npx skills add https://github.com/devMoez/titan --skill qmd-devmoez
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/devMoez/titan/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/devMoez/titan --skill qmd-devmoez
QMD eliminates the frustration of hunting through scattered notes, meeting transcripts, and docs by giving you fast, accurate local search across large markdown/text collections.
Run: qmd collection add ~/notes --name notes, then run: qmd embed, and finally search with: qmd query "what did we decide about the database migration" .
High-intent search queries and answers about installing and using this skill.
You can search local notes on-device by indexing your text and markdown files with a local knowledge base tool. This eliminates manual scanning and reliance on cloud services by enabling fast, accurate retrieval directly from your machine.
Hybrid RAG retrieval combines BM25 keyword matching, vector semantic search, and LLM-based reranking to find relevant notes. You need it for difficult queries where pure keyword or semantic search alone fails to locate relevant documents accurately.
To set up local vector search and BM25 indexing, add your text directory to a collection, generate embeddings, and execute queries. This indexes your markdown and text files locally for fast, accurate retrieval.
Yes, you can expose local document search tools to MCP-driven agent workflows. This allows agents to query and retrieve documents from indexed collections directly through the Model Context Protocol for seamless automation.
Yes, local RAG search works directly in the command line interface. You can manage collections, generate embeddings, and execute hybrid queries across your indexed text files entirely through CLI commands.
LLM-based reranking requires generating embeddings and local indexing with BM25 and vector search. The limitation is the processing overhead for higher-quality ranking, which demands local compute resources for difficult queries.
cloudlinessSearch local markdown notes and transcripts with hybrid BM25 and vector retrieval.
AxelooooImplement RAG pipelines with vector retrieval and context-grounded generation.
devMoezConnect Titan Agent to MCP servers and register discovered tools.
sheawinklerSearch local markdown and text collections using hybrid BM25 and vector ranking.
