Tag: #bm25
6 packages âĸ â 6,388 total stars
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.
The memory system your AI agent deserves. 4-stage hybrid retrieval â Vector + BM25 + Knowledge Graph + Neural Reranker â in <150ms. Self-hosted, $0/query, built for agents that need to actually rememb
Agentic memory built on Postgres
đ Enable smart document and data search with AI-powered chat, vector search, and SQL querying across multiple file formats.
đ Build memory and retrieval infrastructure for ReasonKit, enhancing data management and access for your applications with ease and efficiency.
