Index local markdown notes, transcripts, and documentation for hybrid search.
npx skills add https://github.com/Rheasilvia/hermes-desktop --skill qmd-rheasilvia
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/Rheasilvia/hermes-desktop/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/Rheasilvia/hermes-desktop --skill qmd-rheasilvia
This skill solves the challenge of fragmented personal knowledge by providing a unified, local search engine that indexes your notes, transcripts, and documentation without relying on cloud services.
Use the qmd skill to perform a hybrid search for information regarding the database migration plan across your project documentation.
High-intent search queries and answers about installing and using this skill.
You can search your local knowledge base using natural language by combining keyword matching, semantic vector search, and LLM-powered reranking to retrieve precise information from indexed markdown notes and transcripts.
Hybrid search for personal knowledge management combines BM25 keyword matching with semantic vector search and LLM-powered reranking to deliver high-precision information retrieval across local files.
Yes, you need Node.js 22 and SQLite with extension support to maintain a persistent, private index of local files for your markdown notes and documentation.
Yes, you can find specific decisions in past meeting transcripts by indexing them locally on-device, which completely avoids the need for cloud services and ensures your data remains private.
Local AI search supports indexing technical documentation across large local project directories, allowing you to quickly locate specific information using natural language queries.
On-device search for a private knowledge base requires specific environment prerequisites like Node.js 22 and SQLite with extension support, and is limited to indexing local files such as markdown notes, transcripts, and documentation.
ldzhhxxIndex and search markdown documents with BM25, vector search, and LLM reranking.
LauraFlorentinRetrieves relevant documents from a knowledge base to ground responses.
jason660519Search local notes and transcripts with hybrid BM25, vector, and reranking retrieval.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
