{"id":1680,"date":"2025-10-09T02:13:25","date_gmt":"2025-10-09T09:13:25","guid":{"rendered":"https:\/\/www.couchbase.com\/com-2026\/products-releases\/"},"modified":"2026-10-20T07:36:21","modified_gmt":"2026-10-20T14:36:21","slug":"products-releases","status":"publish","type":"page","link":"https:\/\/www.couchbase.com\/de\/products\/releases\/","title":{"rendered":"Product Release"},"content":{"rendered":"
\n
\n
\n

COUCHBASE RELEASE<\/p>\n\n\n\n

Smarter Agents and Insights, Right Where Your Data Lives<\/h1>\n\n\n\n

Agent Memory and MCP Server join the managed AI Data Plane services in Couchbase Capella, with serverless models and private embeddings. And Couchbase Analytics is now Operational Insights.<\/p>\n\n\n\n

\n
Mehr erfahren<\/a><\/div>\n\n\n\n
Blog lesen<\/a><\/div>\n<\/div>\n<\/div>\n\n\n\n
\n
\"\"<\/figure>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n
\n
\n

20+<\/p>\n\n\n\n

ready-made MCP Server tools, read-only by default<\/p>\n<\/div>\n\n\n\n

\n

94%<\/p>\n\n\n\n

recall on LongMemEval-M single session<\/p>\n<\/div>\n\n\n\n

\n

1<\/p>\n\n\n\n

SQL query to group by semantic meaning and aggregate<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

The Couchbase you know gets even better for agents<\/strong><\/h2>\n\n\n\n

Agent Memory and MCP Server now run fully managed in Couchbase Capella, alongside Agent Catalog and the rest of the AI Data Plane. And Couchbase Analytics has a new name, Operational Insights, with powerful new ways to search and group data by semantic meaning in SQL.<\/p>\n<\/section>\n\n\n\n

\n
\n
<\/svg><\/div>\n\n\n

Fully managed<\/h2>\n\n\n\n

Couchbase installs, patches, and upgrades managed Agent Memory and MCP Server for you.<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
<\/svg><\/div>\n\n\n

Same APIs, two deployments<\/h2>\n\n\n\n

Agent Memory and MCP Server use the same model and APIs whether Capella runs them or you do.<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
<\/svg><\/div>\n\n\n

Data stays secure in your perimeter<\/h2>\n\n\n\n

Embeddings travel over private networking to Amazon Bedrock, and your operational data stays in Couchbase.<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
<\/svg><\/div>\n\n\n

Analytics, renamed and upgraded<\/h2>\n\n\n\n

Operational Insights now supports vector search, semantic clustering, and Python UDFs (self-managed).<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/section>\n\n\n\n

\n
\n

New AI Data Plane capabilities, built for production<\/h2>\n\n\n\n

Streamline deployment of AI agents from pilot to production with persistent Agent Memory, Apache Iceberg lakehouse federation, and Rust support. And for mobile, Bluetooth peer-to-peer sync and React Native support.<\/p>\n<\/section>\n\n\n\n

\n
\n
\n
<\/svg><\/div>\n\n\n

Managed Agent Memory<\/h2>\n\n\n\n

Durable agent memory as a Capella service, with TTL-based decay, conflict resolution, and OIDC\/OAuth2 built in.<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
<\/svg><\/div>\n\n\n

Managed MCP Server<\/h2>\n\n\n\n

A remote, single-tenant MCP server in your Capella environment, with ready-made tools and read-only defaults.<\/p>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

\n
\n
<\/svg><\/div>\n\n\n

Serverless frontier models<\/h2>\n\n\n\n

Claude, Llama 4, Nova, Mistral, and Cohere from Amazon Bedrock. Pay per token, with no GPUs to size or reserve.<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
<\/svg><\/div>\n\n\n

Private Bedrock vectorization<\/h2>\n\n\n\n

Generate embeddings with your own Amazon Bedrock account over AWS PrivateLink, off the public internet.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/section>\n\n\n\n

\n
\n

Couchbase Analytics is now Operational Insights<\/strong><\/h2>\n\n\n\n

Same foundation, new name. Capella Analytics is now Capella Operational Insights, and Enterprise Analytics is now Enterprise Operational Insights. The latest version adds vector search, semantic clustering and Python UDFs (arriving first for self-managed deployments).<\/p>\n<\/section>\n\n\n\n

\"\"<\/figure>
\n
\n
\n

Vector search in SQL<\/strong><\/h2>\n\n\n\n

Self-managed deployments let you search by meaning in plain SQL. Vectors and a VTREE index keeps approximate search fast at scale. No separate vector database.<\/p>\n<\/div>\n\n\n\n

\n

Semantic clustering<\/strong><\/h2>\n\n\n\n

CLUSTER BY groups by meaning, then counts and aggregates each group in the same query. Find themes in reviews, tickets, or claims without manual tagging (self-managed).<\/p>\n<\/div>\n\n\n\n

\n

Python UDFs<\/strong><\/h2>\n\n\n\n

Write custom functions in Python and call them from SQL on self-managed deployments. Run your own ML models where the data lives, with no export to a separate service.<\/p>\n<\/div>\n\n\n\n

\n

Faster, leaner queries<\/strong><\/h2>\n\n\n\n

Query plan caching skips planning for repeat queries, hash-based aggregation counts DISTINCT values in one pass, and sampled optimizer stats avoid full-table scans.<\/p>\n<\/div>\n\n\n\n

\n

Multi-statement queries<\/strong><\/h2>\n\n\n\n

Send several SQL++ statements in one request, so multi-step analysis needs less application code.<\/p>\n<\/div>\n\n\n\n

\n

One product, two deployments<\/strong><\/h2>\n\n\n\n

Capella Operational Insights is fully managed in the cloud. Enterprise Operational Insights runs on the same foundation on premises or in your own cloud.<\/p>\n<\/div>\n<\/section>\n<\/div><\/div>\n<\/div>\n\n\n\n

\n
\n

One platform for data, memory, and models<\/h2>\n\n\n\n

Your operational record, agent memory, governed access, models, and insights run on one Couchbase foundation, with SQL++ across operational and analytical data. That means fewer systems to keep in sync and one place to set access rules.<\/p>\n<\/section>\n\n\n\n

\n
\n
\n

Context that carries over<\/h2>\n\n\n\n

Agents keep durable facts, decaying context, and semantic recall in one JSON store. Users stop repeating themselves, and your team stops syncing separate memory systems.<\/p>\n<\/div>\n\n\n\n

\n

Access control in one place  <\/strong><\/h2>\n\n\n\n

The Couchbase MCP Server gives every agent and tool one open-standard front door to governed Couchbase data, instead of a custom integration per agent where permissions can drift.<\/p>\n<\/div>\n\n\n\n

\n

Lower cost to run AI<\/h2>\n\n\n\n

Right-sized context trims token spend on every call, and per-token model pricing means no idle GPUs to pay for.<\/p>\n<\/div>\n\n\n\n

\n

Insight your agents can use <\/h2>\n\n\n\n

Write Operational Insights results back to Couchbase, where apps and agents act on them on the next read through the AI Data Plane.<\/p>\n<\/div>\n<\/section>\n<\/div>

\"\"<\/figure><\/div>\n<\/div>\n\n\n\n
\n
\n

Was die Kunden sagen<\/h2>\n<\/section>\n\n\n\n
\n