Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a conceptual fork of OrientDB, the first Multi-Model DBMS. ArcadeDB supports Vector Embeddings.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
The unified database engine: native SQL, vector search (HNSW), and columnar storage in one Rust engine — from an embedded file to a distributed cluster.
Code similarity search by compression - find near-duplicate files, clone families, and where a pasted snippet came from. No embeddings, no model, no vector database.
TORoidal Approximate Nearest Neighbours. Exact + LSH k-NN and range search under wrap-around L1 on the unit torus, where opposite faces are identified so the domain has no boundary. The LSH only filters; distances are always exact. Rust core (PyO3 + rayon), byte-identical pure-Python reference.
Python SDK for Aetherfy Vectors — a drop-in replacement for qdrant-client with global sub-50ms latency, built-in analytics, workspace scoping, and client-side payload schema validation.