Index local markdown notes, transcripts, and docs for hybrid on-device search.
npx skills add https://github.com/ChimeraFoundationa/Agentx --skill qmd-chimerafoundationa
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/ChimeraFoundationa/Agentx/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/ChimeraFoundationa/Agentx --skill qmd-chimerafoundationa
Personal knowledge management often requires deep searching across notes, docs, and transcripts, which is slow and fragmented when using generic tools.
Install qmd, create a collection of documents, and run your first search to see results locally.
High-intent search queries and answers about installing and using this skill.
To search markdown notes locally without cloud dependencies, use an on-device indexing tool. It operates entirely offline, indexing your local documentation and returning search results directly on your machine.
Hybrid retrieval ranking combines BM25 keyword search, vector similarity, and LLM reranking to improve local search. This multi-layered approach captures exact term matches and semantic context, producing highly accurate results from indexed documents.
Yes, you can use local search with Hermes Agent through optional MCP integration. This connection enables streamlined automation and workflows, allowing your agent to query indexed markdown notes and transcripts directly.
Yes, you need Node.js version 22 or higher to run this local knowledge search. This environment provides the necessary runtime capabilities to index markdown notes, meeting transcripts, and documentation on your device.
The best way to find specific information across fragmented meeting transcripts is using a local search tool with hybrid retrieval. It indexes transcripts on-device and uses BM25, vector search, and LLM reranking to quickly surface exact answers.
cxnaiveIndex local markdown notes and perform hybrid semantic search with BM25 and vector embeddings.
robwestzSearch an indexed knowledge base with natural language and return semantically ranked results.
Yangel-hideSearch local knowledge stores with hybrid BM25, vector, and LLM reranking.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
