Index and query markdown notes with hybrid BM25 and vector search.
npx skills add https://github.com/zangjeicy/Hermes --skill qmd-zangjeicy
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/zangjeicy/Hermes/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/zangjeicy/Hermes --skill qmd-zangjeicy
This skill solves the difficulty of finding specific information across fragmented personal knowledge bases, notes, and meeting transcripts by providing a local, privacy-focused search engine.
Use the qmd skill to perform a hybrid search for your notes regarding the database migration plan.
High-intent search queries and answers about installing and using this skill.
To search markdown notes locally, you can use a hybrid search engine that indexes your files using BM25 keyword matching and semantic vector retrieval, ensuring your private knowledge base remains secure on your device.
Hybrid retrieval for a personal knowledge base combines BM25 keyword matching, semantic vector search, and LLM-powered reranking to provide high-precision information discovery across fragmented markdown notes and meeting transcripts.
Yes, you need Node.js and SQLite installed in your environment to run this local semantic search engine, as these dependencies handle the execution environment and data indexing without requiring cloud services.
Yes, you can integrate local search with MCP to enable seamless agentic access to your personal knowledge base, allowing AI agents to query your indexed markdown notes and meeting transcripts directly.
The best way to find specific decisions in meeting transcripts is using a local hybrid search engine that applies LLM reranking and semantic vector retrieval to accurately locate relevant information via natural language queries.
Cloud-based search for personal notes introduces privacy risks, whereas a local hybrid search engine runs entirely on-device with no cloud dependencies, ensuring your private meeting transcripts and documentation remain secure.
superfhpIndex and query markdown notes with BM25, vector search, and LLM reranking.
LauraFlorentinRetrieves relevant documents from a knowledge base to ground responses.
yusufcmgImplement Retrieval-Augmented Generation systems with vector databases and semantic search.
Rawgrowth-ConsultingIndex and query vectors in a managed serverless vector database.
