Index local notes and search with BM25, vector search, and LLM reranking.
npx skills add https://github.com/Harries/hermes-agent --skill qmd-harries
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/Harries/hermes-agent/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/Harries/hermes-agent --skill qmd-harries
Local knowledge collections sit idle without fast, privacy-preserving search. QMD enables on-device indexing and retrieval over notes, docs, transcripts, and files using a hybrid approach that blends traditional keyword search with semantic vectors and LLM reranking.
Index your local notes and run a hybrid bm25+vector search to locate relevant information across your knowledge base.
High-intent search queries and answers about installing and using this skill.
Search local notes and transcripts offline using a hybrid retrieval engine that combines BM25 keyword search, vector search, and LLM reranking directly on your device.
Hybrid retrieval for personal knowledge management blends traditional BM25 keyword matching with semantic vector search and LLM reranking to locate relevant information across local documents.
Yes, you can index project documentation on macOS without cloud dependencies because the system operates fully offline, relying on local storage for the index and locally cached models.
Yes, local knowledge base search supports MCP integration, allowing seamless tool availability and connectivity within your existing offline workflows and private data environments.
Limitations of offline search include requiring local storage capacity for indices and embeddings, and needing locally cached models and tooling, which may consume significant disk space on your device.
peteromalletIndex and search local markdown and text documents with hybrid retrieval.
beyonaiAggregate calendar events, attendee context, and task priorities into a daily briefing.
lanejSearch and audit personal knowledge bases with hybrid vector and BM25 indexing.
Chris-Chai-MinjaeIndex local text files for hybrid keyword and semantic search.
