Enable local hybrid search across markdown notes and documents.
npx skills add https://github.com/AissenLiu/EasyHermes --skill qmd-aissenliu
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/AissenLiu/EasyHermes/tree/main/hermes-agent/optional-skills/research/qmd Command: npx skills add https://github.com/AissenLiu/EasyHermes --skill qmd-aissenliu
Private, local search over your notes, docs, and transcripts, enabling fast retrieval without cloud dependencies.
Run a local search across your markdown notes and transcripts to retrieve the most relevant documents.
High-intent search queries and answers about installing and using this skill.
You can search local markdown notes and transcripts offline by utilizing a hybrid retrieval system. It uses BM25, vector search, and LLM reranking to index and query your private documents without cloud dependencies.
Hybrid retrieval for local knowledge bases combines BM25 keyword matching, vector search, and LLM reranking. This multi-layered approach ensures fast and highly relevant document discovery directly on your device.
Yes, local knowledge search supports seamless MCP and CLI integrations. This allows you to index and query your local documents directly within Hermes Agent workflows for quick retrieval.
Yes, you need Node.js version 22 or higher to run local vector search and indexing. The system operates offline using a local model cache and your MCP configurations.
You can retrieve documents from meeting transcripts without cloud dependencies by running local on-device search. It indexes your transcripts and documents locally, ensuring private and fast retrieval.
The best way to index local documents for private search is using a local on-device tool that supports hybrid ranking. This enables indexing markdown notes and transcripts for quick discovery while keeping data offline.
ChimeraFoundationaIndex local markdown notes, transcripts, and docs for hybrid on-device search.
anilcan-karaIndex and search local knowledge bases with hybrid retrieval via CLI and MCP.
cxnaiveIndex local markdown notes and perform hybrid semantic search with BM25 and vector embeddings.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
