Weaviate
used in
0
stacks
Open-source, cloud-native vector database in Go that stores both objects and vectors.
BSD-3-Clause licensed vector database written in Go that stores objects alongside their vectors and supports hybrid (vector plus keyword) search. Offers built-in embedding generation, multi-tenancy at large tenant counts, RBAC, and SDKs for Python, TypeScript/JavaScript, and Go. Runs self-hosted or on Weaviate Cloud, which has a free shared tier, usage-based pricing, and dedicated enterprise options.
Strengths
- Hybrid vector plus BM25 keyword search in a single query API
- Built-in vectorizer integrations generate embeddings at ingest time
- Multi-tenancy designed for tens of thousands of tenants
- Enterprise features including RBAC, SOC 2, and HIPAA compliance options
Tradeoffs
- HNSW indexes are memory-hungry, driving up infrastructure cost at large scale
- Collection/schema and module configuration adds setup complexity versus simpler stores
- Expanding product surface (agents, embeddings, memory) increases the learning surface beyond core vector search