Key Points
- Couchbase AI Data Plane now generally available for enterprise AI agent deployments
- Platform unifies agent memory, context retrieval and data access from cloud to edge
- Trino adapter for lakehouse integration expected in third quarter of calendar 2026
Database software company Couchbase has launched its AI Data Plane, a unified data infrastructure platform designed to help enterprises deploy production-grade artificial intelligence (AI) agents by providing persistent memory, real-time data access and context retrieval across cloud, edge and on-premises environments.
The company said the platform addresses one of the biggest hurdles in enterprise AI adoption by consolidating multiple data services—including vector search, document storage, caching and operational data—into a single governed layer, enabling organisations to move AI projects from pilot stages to production.
The AI Data Plane combines Agent Memory, an Agent Catalog for discovering AI tools, and a self-managed Model Context Protocol (MCP) server for integrating AI models with enterprise data. It also unifies Couchbase’s deployment architecture across its cloud-based Capella platform and self-managed environments.
Alongside the launch, Couchbase introduced Enterprise Analytics 2.2, adding support for Apache Iceberg lakehouse federation and announcing a Trino adapter, expected in the third quarter of 2026, to enable SQL access to operational data without requiring data replication.
“Most enterprises quickly discover that moving from chat-style pilots to production-grade agentic systems is really a data problem, not just a model problem,” said Devin Pratt, Research Director for AI, Automation, Data and Analytics at IDC.
According to IDC, about 80% of agentic AI use cases will require real-time, contextual and widely accessible data, making the underlying data architecture critical for enterprise deployments.
Couchbase – Framework-agnostic layer
Couchbase said its Agent Memory capability provides a framework-agnostic persistence layer compatible with orchestration platforms including LangGraph, CrewAI and LlamaIndex, allowing organisations to switch frameworks without rebuilding their data infrastructure.
The company said its architecture is designed to support high-volume AI workloads, with its memory-first distributed platform capable of handling tens of millions of transactions per second with sub-millisecond latency.
The release also includes updates to Capella iQ, Couchbase’s natural language query assistant, adding support for multiple AI model providers, including AWS Bedrock and OpenAI, while allowing enterprises to manage model access, compliance and inference costs through centralised policies.
For edge deployments, Couchbase announced updates to Couchbase Lite, Edge Server, React Native support and Sync Gateway, enabling AI agents operating on mobile devices and edge environments to access replicated data and perform local vector search even during intermittent connectivity.
“The database layer is where agentic AI either scales or stalls,” said Barry Morris, Chief Product and Strategy Officer at Couchbase. “Agent Memory gives customers a unified, framework-agnostic persistence layer that operates identically across cloud and self-managed environments.”
Your Questions, Answered
What is the Couchbase AI Data Plane?
The AI Data Plane is a unified data infrastructure layer that provides AI agents with persistent memory, real-time context retrieval and consistent data access across cloud, edge and lakehouse environments.
What problem does the AI Data Plane solve?
It addresses fragmented data services that have slowed enterprise AI agent deployments by consolidating vector stores, caching, document storage and agent memory into a single governed platform.
When will the Trino adapter be available?
Couchbase expects the Trino adapter, which provides SQL access to operational data from platforms like AWS Athena and Google Dataproc, to launch in the third quarter of calendar 2026.
What is Apache Iceberg lakehouse federation?
It allows organisations to query real-time operational data from Couchbase alongside existing Iceberg-based lakehouse tables without complex data extraction or duplication processes.
