Video
AGENT MEMORY TRIAL
The data layer for production AI agents
Couchbase AI Data Plane gives production AI agents persistent memory, governed data access, tool and prompt visibility, and fast context retrieval across cloud, self-managed, hybrid, edge, and air-gapped environments. It brings Agent Memory, MCP Server, and Agent Catalog together on Couchbase, helping teams avoid scattered agent infrastructure and move from pilots to production-ready systems faster.
Give production AI agents memory, governance, speed, and cost control
Govern AI
Keep prompts, tools, traces, memory, and operational data in one governed data layer so teams can inspect agent behavior with SQL++.
Give agents memory
Maintain short-term, long-term, semantic, profile, and conversational memory across sessions, restarts, users, and frameworks.
Connect agent data
Give agents standardized access to Couchbase operational data, vectors, documents, tools, prompts, traces, and cache.
Control costs
Reduce redundant LLM calls with exact and semantic caching while keeping cache, vectors, documents, and operational data together.
Couchbase AI Data Plane
Couchbase AI Data Plane combines Agent Memory, MCP Server, and Agent Catalog on a JSON-native, memory-first architecture. It lets agents retain context and access data via standard protocols, cutting redundant inference calls while providing visibility via SQL++.
Agent Memory
Give agents persistent memory across sessions, restarts, and frameworks, kept close to your operational data.
MCP Server
Give agents standardized access to Couchbase operational data, vectors, documents, and cache via MCP.
Agent Catalog
Manage prompts, tools, metadata, and end-to-end traces so teams can inspect, reuse, and govern agent behavior.
AI Functions
Utilize SQL++ and AI functions to utilize LLMs for tasks like analyzing sentiment, summarizing text, and more.
Governed AI & agents
Production agents need access to memory, tools, prompts, operational data, traces, and context, but those assets often live in scattered systems. Couchbase keeps them in one governed data layer, giving teams visibility into what an agent used, which prompt version was involved, and what data shaped the response.
Fast context at scale
Production agents need fast access to current context across operational data, vectors, documents, memory, and cache. Couchbase keeps those assets close together, reducing data hops and helping agents respond quickly across cloud, self-managed, hybrid, edge, and air-gapped environments.
Powerful vector search
Couchbase’s advanced vector search delivers billion-scale storage and search with exceptional performance. It enables rich context across text and images while ensuring scalability, security, and seamless AI tool integration. Move from prototype to production with three indexing options tailored to any use case.
Automating context pipelines
Organizations often overlook unstructured data that could enhance AI. Couchbase automates data ingestion, vectorization, and indexing converting text, PDFs, and images into JSON and vectors. It automatically re-vectorizes updates to streamline workflows and give models richer context.
One data layer for agents
Couchbase provides the data foundation for critical AI apps and agents, helping teams store LLM interactions, connect agents to governed operational data, reduce custom memory and retrieval code, cut latency and token costs, and run across cloud, self-managed, hybrid, edge, and air-gapped environments.
What customers are saying
“Couchbase real-time communications data and high concurrency query, greatly improve the performance and stability for the AI Assistant application.”
70M
documents
8K
operations per second
“As we’ve scaled into agentic workloads, this was a natural extension to our partnership.”
0.5
second agentic transaction target
4
real work agentic AI use cases
“The ability to run queries easily helped us boost the machine learning AI algorithms that we’re running today. Couchbase was the database for us.”
60%
reduction in operating costs
50%
decrease in street and area lighting costs
“We found that the replication technology across data centers for Couchbase was superior, especially for the large workloads.”
<1ms
response times
24x365
application uptime
Integrates with your agent and AI ecosystem
Build with leading AI, data, and observability partners while keeping agent memory, context, tools, traces, and cache secured on Couchbase.
AI Data Plane resources
See Couchbase AI Data Plane in action
Your AI agents are stuck in pilot. It's a data problem, not a model problem.
Learn more details about AI Data Plane
AI Data Plane (formerly AI Services) FAQ
Get quick answers about agent memory, governed data access, LLM caching, security, and production AI agents.
What is Couchbase AI Data Plane?
Couchbase AI Data Plane provides production AI agents with one governed data layer for memory, context, tools, traces, operational data, and cache.
How does AI Data Plane help agents remember?
Agent Memory maintains short-term and long-term memory across sessions, restarts, users, and frameworks while keeping memory close to operational data.
How does Couchbase govern agent behavior?
Couchbase keeps prompts, tools, traces, memory, and operational data in one governed data layer so teams can inspect what agents used and why they responded.
What does the Couchbase Agent Catalog do?
Agent Catalog manages prompt metadata, tool metadata, and end-to-end traces so teams can inspect, reuse, and govern agent behavior across applications.
How does AI Data Plane reduce AI costs?
Agent Memory reduces token costs by reusing persistent, cumulative context instead of resending conversations each turn, while co-located data and caching cut redundant inference calls.
Is AI Services now called AI Data Plane?
Yes, AI Services has officially rebranded to AI Data Plane as of June 2026. The product has evolved under the AI Data Plane identity to support new features.
Start building
Explore docs, tutorials, and examples for building production AI agents with Couchbase.
Use Capella free
Get hands-on with Couchbase and start building agent-ready applications in just a few clicks.
Get in touch
Talk with Couchbase about moving AI agents from pilot to production.