ruvector-core

A simple, easy-to-hack vector database library implemented in Rust. It supports fast cosine similarity searches with Rayon parallelism, embedded persistence, and a minimal API ideal for prototyping and educational purposes.

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.

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.

Pure-Rust implementation of HNSW algorithm for approximate nearest neighbor search. Decouples graph from vector storage for flexible deployment. Supports dense floating point and quantized int8 vectors. This is an OSS library.

PostgreSQL extension for scalable, low-latency vector search written in Rust. Features 20x faster HNSW than pgvector, with support for FP16, INT8, and binary vectors. This is an OSS extension.