AtlasDB

Distributed NoSQL database with vector search capabilities via Storage-Attached Indexes (SAI) in Cassandra 5.0+. Uses Lucene HNSW for approximate nearest neighbor search. This is an OSS database under Apache 2.0 license.

Real-time distributed SQL database with vector search capabilities, combining transactional, analytical, and vector workloads in a single engine for hybrid AI applications.

Open-source distributed graph database designed for super large-scale graphs with billions of vertices and trillions of edges. Outperforms Neo4j on larger datasets while providing graph database capabilities for AI applications.

Distributed key-value NoSQL database with experimental vector similarity search. Redis-compatible with RocksDB storage engine, adding HNSW-based vector indexing for large-scale vector data management.

Milvus is a high-performance, open-source vector database designed for managing massive-scale embedding vectors in AI applications. It excels in similarity search using advanced indexing like HNSW and IVF, supports distributed deployment for billions of vectors, GPU acceleration, and hybrid search combining vector and scalar filters. Key use cases include RAG pipelines, recommendation engines, and image/video retrieval; it outperforms single-node DBs like Faiss in scalability but requires more setup compared to managed options like Pinecone.

SIGKDD 2022 paper introducing BLISS, a billion-scale indexing method using iterative re-partitioning for large-scale approximate nearest neighbor search.