Weaviate

Weaviate develops and operates Weaviate, an open-source vector database that serves as the foundation for AI applications requiring semantic search, retrieval-augmented generation (RAG), and agentic capabilities. A vector database stores content as numeric vectors, letting it find similar meanings rather than only exact word matches. The official MCP server has been built directly into the database server since version 1.38, rather than running as a separate component.

The platform unifies four core capabilities: a vector database for storing and querying embeddings, built-in embedding generation directly from text and images, a Query Agent that translates natural-language questions into optimized database queries, and "Engram" for personalized AI experiences that adapt to individual users over time. Access is available via Python, Go, TypeScript, and JavaScript SDKs, as well as GraphQL and REST APIs.

The business model is dual: the core database remains open source with more than 20 million downloads, while the company offers commercial cloud services with free and usage-based tiers, plus enterprise deployment options. Enterprise features include multi-tenancy, role-based access control, and SOC 2 and HIPAA certification.

The project was founded in Amsterdam in 2016 by Bob van Luijt, together with Etienne Dilocker and Micha Verhagen, originally under the name SeMI Technologies; customers today include Booking.com, Cisco, and Intuit.