What problem does it solve? Finding information across large collections of personal notes, meeting transcripts, and documentation is slow with plain keyword grep and impossible with conceptual questions. This Skill indexes local text files and retrieves answers using keyword matching, semantic vector search, and LLM reranking, all running on-device with no cloud dependencies. ## Core Features & Use Cases - Three Search Modes: BM25 keyword search for exact terms, vector search for conceptual queries, and hybrid query mode combining both with LLM reranking for best quality. - Collection Management: Add directories as named collections, attach context descriptions to improve retrieval accuracy, and generate embeddings with a single command. - MCP Integration: Expose search tools directly to Hermes Agent via stdio or a persistent HTTP daemon that keeps models warm for fast repeated queries. - Use Case: A user asks "what decisions were made about the database migration" and the hybrid query pipeline searches meeting transcripts and project docs, returning reranked excerpts with document IDs for full retrieval. ## Quick Start Ask the agent to search your notes for a specific topic, for example: "Search my knowledge base for notes about the API redesign decisions."
