Couchbase unveiled a unified data infrastructure layer for enterprise AI agents.

Dubbed the AI Data Plane, the layer seeks to provide an operational stratum for AI agents with persistent memory, context retrieval, and data from the cloud to the edge. By closing gaps across fragmented data services, Couchbase claims its offering can help enterprise agents make consistent decisions at scale.

"The database layer is where agentic AI either scales or stalls, and most of the industry is still treating agent memory as an afterthought," Couchbase Chief Production and Strategy Officer Barry Morris noted. "We built the AI Data Plane because our customers told us that stitching together separate vector, caching, and document stores for every agent was the single biggest drag on their production timelines.”

Data platform vendors have routinely made the point that their enterprise customers have undiscovered gems hidden in disparate pools of structured and unstructured data. By establishing a single distributed platform that merges vectors, documents, caching, and operational data, Couchbase's AI Data Plane aims to minimize the burdensome management of retrieving relevant information from those sources.

Such a space is already increasingly contested, with Couchbase joining a roster of established vendors. Heavyweights like Databricks’ Unity Catalog and Snowflake’s Horizon platform were recently joined by Everpure (formerly Pure Storage) with its Data Intelligence offering.

Couchbase touts its offering in that it brings together Agent Memory, a catalog for discoverable agent tooling, and an enterprise-supported, self-managed model context protocol (MCP) server that runs across its Capella and self-managed environments. The AI Data Plane also leans on the vendor’s distributed multimodel architecture, which supports JSON documents, key-value, and SQL for JSON queries in one sole system.

“Agent Memory gives them a unified, framework-agnostic persistence layer that operates identically in cloud and self-managed environments from cloud to edge, and runs at the latency their agents actually need,” Morris added. “That's what it takes to move from pilot to production – and the vendors who understand this will define the infrastructure category for the next decade of AI.”

Conversational AI platform Agora counts among the early adopters of Couchbase’s offering.

“Every one of our conversational AI use cases requires efficient data retrieval to feed the pipeline for AI agents, whether that's outbound sales, customer service, physical AI, or something entirely new," Patrick Ferriter, SVP of product at Angora, noted. "We've had a multi-year relationship with Couchbase, and as we've scaled into agentic workloads, this was a natural extension to our partnership.”

The launch of AI Data Plane marks the biggest update from Couchbase since it went private last September after it was acquired by Haveli Investments in an all-cash deal worth $1.5 billion.