Search local markdown and text collections with hybrid retrieval and reranking.
npx skills add https://github.com/eddielueng/hermes-agent-zh --skill qmd-eddielueng
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/eddielueng/hermes-agent-zh/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/eddielueng/hermes-agent-zh --skill qmd-eddielueng
qmd eliminates the frustration of manually searching large personal document collections by combining fast keyword matching with semantic retrieval and LLM reranking.
Tell Hermes Agent: "Search my qmd collections for decisions made about the database migration and return the most relevant notes."
High-intent search queries and answers about installing and using this skill.
Local search across markdown notes uses hybrid retrieval, combining BM25 keyword matching with semantic vector search and LLM reranking to find exact terms and conceptually related text across your personal knowledge base.
RAG queries can be scoped to specific named collections of meeting transcripts, allowing targeted retrieval over indexed documents by organizing files into collections and optionally adding context descriptions for better results.
Hybrid retrieval works with Hermes Agent by exposing searchable collections through a configurable MCP server, enabling the agent to query your local knowledge base and return relevant notes on demand.
Combining keyword and semantic search for a personal knowledge base requires a hybrid approach that runs BM25 exact term matching alongside vector embedding retrieval, followed by LLM reranking to surface the most relevant documents.
Local indexing of text and markdown files is required before querying, organizing documents into named collections with optional context descriptions to enable accurate hybrid retrieval and reranking.
You can search local notes directly from the command line using CLI integration, querying indexed collections to retrieve relevant information without needing to expose the search tools through an MCP server.
davpatel605-beepSearch local markdown notes and transcripts using hybrid keyword and vector retrieval.
anukkrit149Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.
devMoezIndex local markdown collections for hybrid BM25 and vector search.
NITISH-gitbitCombine BM25 keyword matching, vector semantic search, and LLM reranking for local Markdown file retrieval.
