Weaviate

Weaviate is an open-source, AI-native vector database with built-in vectorizer and generative modules, hybrid search, and multi-tenancy. It can be self-hosted for free or used as a managed cloud service. It is popular for RAG and semantic search when teams want flexibility across deployment models.

Weaviate is an open-source, AI-native vector database written in Go that stores objects alongside their vector embeddings and supports fast similarity search, hybrid (keyword plus vector) search, and metadata filtering. Its distinguishing feature is a modular architecture with built-in vectorizer and generative modules, so it can generate embeddings and even orchestrate RAG-style generation directly, rather than requiring you to compute vectors entirely outside the database. Weaviate is available under an open-source license (BSD/Apache-style) that you can self-host for free, and as Weaviate Cloud, a managed service with a free sandbox and paid tiers billed roughly by vector dimensions stored. This flexibility across self-hosted, managed cloud, and hybrid deployments is a core selling point for teams that want to avoid lock-in or keep data in their own environment. The project has invested heavily in features for production RAG and agentic applications, including multi-tenancy, replication, hybrid search tuning, and integrations across the LLM ecosystem. It competes directly with Pinecone, Qdrant, Milvus, and Chroma, differentiating on its module system and open-source flexibility.