Releasesby GlyphDedicated Memory Bank functionality in the Google Cloud console
Users can now create, configure, and inspect Agent Platform Memory Bank instances through a dedicated page in the Google Cloud console. The update provides centralized memory management, including structured and unstructured memory filtering and revision history.
Also shipped Nov 6, 2026Google Cloud in November 2026 →
Kimi K3.1 Pro (Highspeed) now available on Amazon Bedrock
Moonshot AI's Kimi K3.1 Pro is now available on Amazon Bedrock. The model features a 1-million-token context window and supports prompt caching for agentic tasks like coding and document processing.
What I learned from a month with WalShadow on ClickHouse Managed Postgres
WalShadow is now available in private preview for ClickHouse Managed Postgres. It allows users to test replication latency, verify data correctness, and manage schema changes and recovery processes.
AWS Glue Data Catalog now supports catalog-vended credentials with Apache Iceberg REST catalog federation
AWS Glue Data Catalog now supports vended credentials for Apache Iceberg REST catalog federation. This allows users to read external Iceberg tables using coarse-grained grants and temporary security credentials scoped to S3 prefixes.
@GitHub in Slack and Teams is generally available and more
@GitHub in Slack and Teams is now generally available, allowing users to investigate bugs, create issues, and open pull requests directly from chat. It also includes Canvas integration for reviewing code and implementation plans.
ClickHouse release 26.10
ClickHouse 26.10 adds function composition, improved join flexibility, faster GROUP BY queries, and disk spilling for IN subqueries. It also includes an experimental columns cache and support for Freeform and SQLite formats.
Unity Catalog wikis are in Beta
Unity Catalog wikis are now in beta, enabling teams to document table meanings and usage directly within Catalog Explorer. Users can collaborate on documentation manually or via Genie Code.
More from Gemini Enterprise Agent PlatformEvery Gemini Enterprise Agent Platform release →
Gemini Omni 1.2 Flash
Gemini Omni 1.2 Flash is now generally available, offering omni-modal processing for text, image, and video. New features include standalone video upscaling, extended generation durations, and reference-guided video editing.
Interactions API long decodes for Gemini 4 Argon
Google Cloud announced general availability for long decodes up to 1,048,576 tokens on the Interactions API for Gemini 4 Argon models using automatic continuation or background execution.
AlphaGenome gRPC and unified HTTP serving support
AlphaGenome now supports unified HTTP/2 gRPC streaming and chunked binary protobuf HTTP streaming, reducing latency for genomic track predictions.
Provisioned Throughput support for supervised fine-tuned models (GA)
Provisioned Throughput support for supervised fine-tuned models is generally available . Burndown rates for fine-tuned model inference can include a premium that's directly proportional to the model's fine-tuned inference pricing premium.
Serving tuned Gemini 3.x models on global endpoints
Serving tuned Gemini 3.x models on global endpoints is available in General Availability (GA) . You can copy fine-tuned Gemini 3.x models to the global region using the Model Registry models:copy API, deploy them to global serving endpoints, and send inference requests directly to aiplatform.googleapis.com .
Inference request metadata logging (GA)
Inference request metadata logging is now generally available for Gemini and Claude models. It records model usage, latency, and error codes without capturing prompt or response content.
Computer use tool is available in General Availability
The Computer use tool is now generally available with new safety governance features. Administrators can configure organization-wide guardrails for sensitive actions like financial transactions or data modification.
Use a single regional Agent Registry instance for Gemini Enterprise apps
Google Cloud updated its guidance for Gemini Enterprise, recommending that each Agent Gateway be associated with a single regional Agent Registry instance in the same project and region.