nano-vectordb-rs

A self-learning, self-optimizing vector database with graph intelligence, local AI runtime, and PostgreSQL integration. It improves search quality over time using GNNs that learn from queries and feedback, supports hybrid search, Graph RAG, DiskANN, and deploys as a single file anywhere including browsers and edge devices. Open-source under MIT license, free forever.

Core Rust crate for the RuVector vector database engine featuring HNSW indexing, SIMD acceleration, and adaptive compression for high-performance similarity search. Supports multi-threaded queries achieving up to 3,597 QPS with 100% recall on 50K vectors. Ideal for AI applications requiring low-latency retrieval in RAG pipelines and agent memory systems.

A tiny embedding database in pure Rust, implemented as a lightweight Axum server for fast vector search on small to medium datasets. It stores all indexes in memory, enabling vertical scaling to over 100 million vectors with comparable speed and slightly better accuracy than advanced vector databases. Open-source under the MIT license, ideal for simple setups like document chat or website search.

Arroy is an open-source library for efficient similarity search and management of vector embeddings, useful in vector database systems.

Qdrant is a production-ready vector similarity search engine with advanced filtering, payload storage, and Rust-based performance. It uses custom HNSW for fast queries, supports dynamic collections, and offers both self-hosted and cloud options. Great for real-time apps like semantic search and RAG; faster than Weaviate in pure vector ops but less feature-rich in ML modules.

Lightweight npm package providing an embedded vector database for Node.js applications. Offers vector similarity search with HNSW, BM25 full-text search, hybrid search using weighted fusion or Reciprocal Rank Fusion (RRF), multi-namespace support, CRUD operations, metadata filtering, concurrency safety, and persistent storage to disk. Designed for RAG pipelines and semantic search use cases.