Couchbase announced the general availability of its AI Data Plane, a unified data infrastructure layer for enterprise AI agents that provides persistent agent memory, real-time context retrieval, and consistent data access from cloud to edge and into lakehouse architectures. The company, known for its NoSQL database with a JSON-like document data model and SQL++ query language, positions itself as the operational data platform for AI. Its Capella AI Services (CAS) Database-as-a-Service offering is available on AWS, Azure, and the Google Cloud Platform, including model hosting, automated vectorization, unstructured data preprocessing, and AI agent catalog services. Couchbase stated that production-grade agents require vector search, storage of conversational context, retrieval of structured operational data, and state maintenance across sessions and restarts “with sub-millisecond latency at the point of decision.” The AI Data Plane unifies Agent Memory, an Agent Catalog, and an enterprise-supported MCP server, consolidating previous deployment models across Couchbase Capella and self-managed environments. This is complemented by new Enterprise Analytics 2.2 capabilities and a Trino adapter expected to launch in Q3 calendar 2026.