freshcrate
Skin:/
Home > #bm25

Tag: #bm25

6 packages â€ĸ ⭐ 6,388 total stars

infinityv0.7.0đŸŒŗ Mature⭐4,485

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

SeekStormv3.2.1đŸŒŗ Mature⭐1,865

SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.

rasputin-memoryv0.9.1🌱 Seedling⭐30

The memory system your AI agent deserves. 4-stage hybrid retrieval — Vector + BM25 + Knowledge Graph + Neural Reranker — in <150ms. Self-hosted, $0/query, built for agents that need to actually rememb

memory-enginev0.2.6🌱 Seedling⭐6

Agentic memory built on Postgres

agentic-ragmain@2026-06-01🌱 Seedling⭐1

📄 Enable smart document and data search with AI-powered chat, vector search, and SQL querying across multiple file formats.

reasonkit-memmain@2026-05-31🌱 Seedling⭐1

🚀 Build memory and retrieval infrastructure for ReasonKit, enhancing data management and access for your applications with ease and efficiency.