Index and retrieve local markdown files using hybrid BM25, vector, and LLM reranking search.
npx skills add https://github.com/zeronx798/demo-hermes-agent --skill qmd-zeronx798
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/zeronx798/demo-hermes-agent/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/zeronx798/demo-hermes-agent --skill qmd-zeronx798
This skill solves the challenge of fragmented personal knowledge by providing a unified, local search engine that indexes your notes, transcripts, and documents without relying on cloud services.
Use the qmd skill to perform a hybrid search for your notes regarding the project architecture.
High-intent search queries and answers about installing and using this skill.
You can search local markdown files and transcripts using a hybrid search pipeline that combines BM25 keyword matching, vector embeddings, and LLM reranking to retrieve precise information from your personal knowledge base.
Yes, you can run semantic search entirely on-device. The local execution operates without cloud dependencies, ensuring your sensitive notes and transcripts remain completely private on your machine.
Yes, performing hybrid search requires Node.js 22 and local GGUF model execution to power the vector embeddings and LLM reranking pipeline for semantic and keyword-based queries.
The best way to find meeting action items is using natural language queries. The hybrid search indexes your documents to retrieve specific decisions and concepts across diverse text collections.
BM25 keyword matching identifies exact term frequencies, while vector search captures semantic meaning, and an LLM reranks the combined results for high-precision document discovery across your notes.
Yes, SQLite is used as a dependency to manage your personal knowledge base, supporting document discovery and cross-session recall across diverse text collections locally.
cxnaiveIndex local markdown notes and perform hybrid semantic search with BM25 and vector embeddings.
jsphh7124Convert academic journals from PDF, Word, PowerPoint, Excel, images, and transcripts into structured Markdown.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
karrtik159Build RAG systems with vector databases and semantic search.
