Index local notes, docs, and transcripts for hybrid BM25 and vector search.
npx skills add https://github.com/objval/hermes-agent --skill qmd-objval
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/objval/hermes-agent/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/objval/hermes-agent --skill qmd-objval
Index local knowledge sources and enable fast, private search across notes, docs, and transcripts.
Ask me to search your local notes with a simple query.
High-intent search queries and answers about installing and using this skill.
Local notes and transcripts search uses on-device indexing with BM25 keyword and vector semantic retrieval to find results offline. It indexes your local files to enable fast, private search without needing cloud connectivity.
Yes, local knowledge-base search supports MCP integration for seamless tooling automation. This allows you to execute on-device workflows and retrieve relevant documents from your personal knowledge base securely.
The best way to retrieve information from markdown notes is using hybrid retrieval. It combines BM25 keyword search, vector-based semantic search, and optional LLM reranking to surface highly relevant results from your documents.
Yes, you can use semantic search for meeting transcripts in secure environments. The local-first workflow supports on-device execution, ensuring your personal knowledge base remains private and accessible offline.
No, you do not need cloud dependencies to index personal documentation. The local-first workflow operates entirely on-device, applying BM25 and vector-based search to your files for private, offline retrieval.
Hybrid retrieval combines BM25 keyword and vector semantic search to balance exact term matching with contextual meaning. Optional LLM reranking further refines these combined results to surface the most relevant information from your knowledge base.
nelohenriqIndex local markdown notes and transcripts for hybrid on-device search via MCP.
softmgImplement semantic vector search with HNSW indexing and multiple distance metrics.
Yangel-hideSearch local knowledge stores with hybrid BM25, vector, and LLM reranking.
hwang847Organize local academic PDFs and generate scoped survey manifests.
