Indexes and searches markdown notes locally using BM25, vector search, vector search and LLM reranking.
npx skills add https://github.com/519lab/thoth-agent --skill qmd-519lab
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/519lab/thoth-agent/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/519lab/thoth-agent --skill qmd-519lab
This Skill solves the problem of efficiently searching through personal knowledge bases, notes, documents, and meeting transcripts locally, without the need for cloud dependencies.
Use the qmd skill to search your notes for information about 'AI development'.
High-intent search queries and answers about installing and using this skill.
You can search local markdown notes and documents entirely on-device using a hybrid search engine that combines BM25 keyword matching, vector search, and LLM reranking, ensuring privacy without cloud dependencies.
The best way to find specific information in a personal knowledge base is using a hybrid search approach that merges keyword matching, semantic vector understanding, and LLM reranking for comprehensive and accurate retrieval.
Yes, you need Node.js and SQLite to operate this local vector search on your notes, as the hybrid search engine requires these dependencies to index documents and manage local queries.
BM25 and vector search work together by first matching exact keywords and then applying semantic understanding to grasp context, followed by LLM reranking to output the most relevant markdown documents.
Yes, you can use this local search engine with CLI and MCP integration to search meeting transcripts, relying on an on-device hybrid search mechanism to quickly find relevant context.
aayushsoamSearch local knowledge bases with BM25, vector search, and LLM reranking.
shsteimerSearch AEM Live documentation and return ranked results with relevance scores.
cxnaiveIndex local markdown notes and perform hybrid semantic search with BM25 and vector embeddings.
LinklyAISearch, browse, and read local and cloud documents indexed by Linkly AI.
