Search local knowledge bases with hybrid BM25, vector, and LLM reranking.
npx skills add https://github.com/GarrettRoi/open-manus --skill qmd-garrettroi
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/GarrettRoi/open-manus/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/GarrettRoi/open-manus --skill qmd-garrettroi
This Skill provides a powerful, local solution for searching personal knowledge bases, notes, documents, and meeting transcripts, overcoming the limitations of simple keyword searches.
Search your personal knowledge base for information about the "database migration plan".
High-intent search queries and answers about installing and using this skill.
Local knowledge base search processes notes, documents, and meeting transcripts entirely on-device. It uses a hybrid retrieval engine combining BM25, vector search, and LLM reranking, ensuring your personal data remains private and never leaves your machine.
Yes, natural language queries can search meeting transcripts and project documentation. The hybrid search engine combines vector semantic search with BM25 keyword matching to understand context and retrieve highly accurate results from your local data.
Local AI knowledge base search integrates with both CLI and MCP for seamless workflow automation. This allows you to trigger searches and retrieve information from your notes and documents directly within your automated command-line processes.
The best way to improve keyword search accuracy for personal notes is using a hybrid retrieval engine. It combines BM25 keyword matching with vector semantic search and LLM reranking to overcome limitations of simple keyword searches and deliver comprehensive results.
No, an internet connection is not required. All models and data are processed locally on your machine, ensuring privacy. The vector search, BM25, and LLM reranking components operate entirely on-device without external network calls.
Simple keyword search misses relevant information because it lacks semantic understanding. Local AI knowledge base search solves this by adding vector semantic search and LLM reranking to BM25 matching, capturing context and meaning to find information that keywords alone miss.
davpatel605-beepSearch local markdown notes and transcripts using hybrid keyword and vector retrieval.
anilcan-karaIndex and search local knowledge bases with hybrid retrieval via CLI and MCP.
FortiumPartnersManage Weaviate collections and run semantic, hybrid, and RAG searches.
ccfDetail distance metrics and index types for vector similarity search across Pinecone, Qdrant, pgvector, and Weaviate.
