{"slug": "couchbase-wants-to-serve-and-remember-data-for-ai-agents", "title": "Couchbase wants to serve and remember data for AI agents", "summary": "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 across cloud, edge, and lakehouse environments. The platform consolidates vector, document, cache, and operational data into a single distributed system to reduce integration complexity and latency for production-grade agentic AI applications.", "body_md": "# Couchbase wants to serve and remember data for AI agents\n\n[Couchbase](https://www.blocksandfiles.com/ai-ml/2024/12/05/couchbase-unveils-capella-ai-services-to-accelerate-agentic-app-development/1612412) says its AI Data Plane, a unified data infrastructure layer for enterprise AI agents, is now generally available, and gives enterprises persistent agent memory, real-time context retrieval, and consistent data access from cloud to edge and into their lakehouse architectures.\n\nThe company is now describing itself as the operational data platform for AI, but is known for producing a NoSQL database, not using the traditional relational database tabular, row-and-column structure or structured query language (SQL). It has a JSON-like document data model with an integrated key-value cache, and a SQL++ SQL-like query language. Data is primarily held in RAM for processing and access speed but persisted to SSDs or disk storage. [Capella AI Services](https://www.couchbase.com/products/ai-services/) (CAS) is its Database-as-a-Service (DBaaS) offering, available on AWS, Azure, and the Google Cloud Platform. CAS includes model hosting, automated vectorization, unstructured data preprocessing and AI agent catalog services. Couchbase competitors include MongoDB and Firebase.\n\nIt says that, as enterprises move AI initiatives from pilot phases to production, with multi-step, autonomous agent architectures, they need a facility for agents to reason and remember context across sessions. Production-grade agents need vector search, the ability to store conversational context, retrieve structured operational data, and maintain state across sessions and restarts, “with sub-millisecond latency at the point of decision.” They also can need to act on structured operational data and unstructured vector embeddings simultaneously across cloud, edge, and devices. Couchbase’s AI Data Plane provides this data and data access base for AI agents.\n\nBarry Morris, Chief Product and Strategy Officer at Couchbase, said: “The database layer is where agentic AI either scales or stalls, and most of the industry is still treating agent memory as an afterthought. 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.\n\n“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. 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.”\n\n**AI Data Plane**\n\nThe AI Data Plane (AIDP) unifies Agent Memory, an Agent Catalog for discoverable agent tooling, and an enterprise-supported, self-managed MCP server for external AI agent data access. It consolidates previous Couchbase deployment models into a single architecture that runs across Couchbase Capella and self-managed environments. This AIDP is complemented by new Enterprise Analytics 2.2 capabilities and a coming Trino adapter, currently expected to launch in Q3 calendar 2026.\n\nThe AI Data Plane is the new name for Capella (managed) AI Services and is also available in self-managed form.\n\nDevin Pratt, Research Director, AI, Automation, Data & Analytics, IDC, provided a supporting statement: \"IDC expects that 80 percent of agentic AI use cases will require real-time, contextual, and widely accessible data, so the architecture has to support that. Approaches that make agent memory and context\n\n“By unifying vectors, documents, cache, and operational data in a single distributed platform, from cloud to edge, Couchbase reduces the integration tax that has been slowing down real-world agent deployments and gives organizations a more governable, scalable foundation for the next wave of AI-powered applications.\"\n\nCouchbase Agent Memory provides a unified persistence layer, combining caching, vector, and document stores as a single service within the operational data platform. Engineering teams can switch or combine orchestration frameworks, because it is framework-agnostic and validated with LangGraph, CrewAI, and LlamaIndex, without rebuilding their memory layer.\n\nEnterprise Analytics 2.2 introduces Apache Iceberg lakehouse federation, allowing teams to query real-time operational analytics from Couchbase alongside existing open Iceberg-based lakehouse tables without complex ETL or data duplication. Couchbase says that this lets enterprises adopt Iceberg for its open governance, performance, and ecosystem benefits and integrate Iceberg tables into the same platform that serves their agentic workloads.\n\nAnalytics enhancements include Google Cloud Storage support, JWT authentication, Oracle and SQL Server change data capture, asynchronous long-running queries, an index advisor, index-only query plans, SQL++ UPDATE support, and corresponding SDK updates across Java, .NET, Python, JavaScript, and Go.\n\nThe Trino adapter will provide in-place SQL access to Couchbase operational data from Trino-based platforms including AWS Athena, Amazon EMR, Google Dataproc, and Starburst. This, Couchbase says, “ eliminates the need for enterprises to extract and replicate live data into separate analytical stores before querying when building AI and analytics workflows that span operational and lakehouse environments.”\n\nCapella iQ, the platform’s natural-language query assistant, now supports multi-model provider selection with AWS Bedrock and OpenAI, governed by organization-level policies.\n\nCouchbase says that, by extending the AI Data Plane to the edge, agents running in mobile and edge environments can access replicated data and perform local vector search, with intermittent or no connectivity.\n\nOther developments include;\n\nCouchbase Lite (CBL) 4.1: Native, out-of-the-box peer-to-peer sync over Bluetooth with automatic switching to Wi-Fi for more reliable collaboration in disconnected edge environments. A modernized Android API with native Kotlin @Serializable support removes boilerplate data mapping and enables efficient, reactive UI updates through direct serialization and delta-based change detection, while new C++ API bindings simplify building high-performance embedded applications.\n\nEdge Server 1.1: Client-level access control for fine-grained local permissions, CORS support for browser-based edge apps, simplified credential rotation for distributed device fleets, and expanded platform support for Windows and ARM architectures.\n\nReact Native 1.1: Enterprise-grade support with Turbo Module integration gives cross-platform mobile teams direct access to Couchbase Lite performance without bridging overhead.\n\nSync Gateway 4.1: Cloud-to-edge data synchronization gateway for non-disruptive rolling upgrades and concurrent distributed resync for high-volume workloads, reducing operational overhead for enterprise deployments. Available as a managed service through App Services.\n\nAll products listed above are available immediately, with the exception of the Trino adapter, coming in Q3. Pricing and packaging details are available at [www.couchbase.com/pricing](http://www.couchbase.com/pricing). More information [here](https://www.couchbase.com/products/releases/ ).\n\n**Exec refresh**\n\nCouchbase has had a near wholesale xec team refresh since BJ Schaknowski was appointed CEO in September last year. He succeeded Matt Cain, who was also Chairman and President, took Couchbase public during his 8+ year reign, and has now, we understand, retired. Amir Jaffrey came on board as the CFO in September as well, but not for long;\n\nDecember 2025: Barry Morris joined as Chief Product and Strategy Officer; Deirdre Toner as President and Chief Commercial Officer, Maggie Warren as Chief Legal Officer.\n\nJanuary 2026: Veronica Curran as Chief People Officer\n\nFebruary 2026: Remington (Chief Business and Transformation Officer), Eddie Garcia (Chief Information Security Officer), and Chelsea Navo (SVP of Customer Success).\n\nMay 2026: Tim Finley hired as SVP of AI. Kari Wimmer appointed as Chief Financial Officer, replacing departed Amir Jafari.\n\nOnly CTO Gopi Duddi and CMO Josh Harbert survive in the CxO team from pre-Schnakowski days.\n\nCouchbase said this about the two most recent exec hires: “Couchbase is seeing significantly increased demand for its operational data platform as the memory and data foundation for agentic AI workloads, with Wimmer and Finley joining as the company scales AI innovation and financial and operational rigor to meet that demand.”\n\n##### Comment\n\nWe recently reported that [LucidLink](https://www.blocksandfiles.com/file/2026/06/29/lucidlink-giving-ai-agents-file-access-with-mcp/5263643) is giving AI agents the same access to real-time, streamed file data as its users and applications, and storing state across and between agents in a workflow. Any and every data store with a vector storage capability will be working out how to provide cross-session and between-agent context memory persisted in storage. It's going to become table stakes.", "url": "https://wpnews.pro/news/couchbase-wants-to-serve-and-remember-data-for-ai-agents", "canonical_source": "https://www.blocksandfiles.com/ai-ml/2026/06/30/couchbase-wants-to-serve-and-remember-data-for-ai-agents/5264312", "published_at": "2026-06-30 12:00:00+00:00", "updated_at": "2026-06-30 13:20:16.777473+00:00", "lang": "en", "topics": ["ai-agents", "ai-infrastructure", "ai-tools", "generative-ai", "large-language-models"], "entities": ["Couchbase", "Capella AI Services", "Barry Morris", "Devin Pratt", "IDC", "AWS", "Azure", "Google Cloud Platform"], "alternates": {"html": "https://wpnews.pro/news/couchbase-wants-to-serve-and-remember-data-for-ai-agents", "markdown": "https://wpnews.pro/news/couchbase-wants-to-serve-and-remember-data-for-ai-agents.md", "text": "https://wpnews.pro/news/couchbase-wants-to-serve-and-remember-data-for-ai-agents.txt", "jsonld": "https://wpnews.pro/news/couchbase-wants-to-serve-and-remember-data-for-ai-agents.jsonld"}}