Releasesby GlyphAtlas Agent Engine in public preview
Atlas Agent Engine is now available in public preview. It provides a secure way to run AI agents at scale.
Also shipped Nov 1, 2026MongoDB in November 2026 →
Kubernetes connector reaches end of life - 02-Nov-202
Snyk announced end-of-life support for the Kubernetes connector (kubernetes-scanner) for Insights, with data ingestion stopping on November 2, 2026.
Qwen Code Release v0.26.5
Qwen Code v0.26.5 adds bounded SQL history queries for H2 and MySQL, enables Generated UI by default, and introduces Web Shell keyboard shortcuts and background agent tracking.
Qwen Code Desktop v0.26.5
Qwen Code Desktop v0.26.5 introduces bounded SQL history queries, enables Generated UI by default, and shows running background agent counts in the status bar.
CrewAI 1.15.34
This update adds a standalone LiteLLM catalog, improves crewai run input handling, and introduces new deployment options. It also includes several bug fixes for tool call telemetry and API key validation.
feldera 0.374.0
This release adds support for STARTSWITH and ENDSWITH string functions, implements NULLIF for mixed-type arguments, and updates date and interval arithmetic to follow the SQL standard. It also includes improvements to the profiler and NATS connector.
More from MongoDB AtlasEvery MongoDB Atlas release →
MongoDB Agents: Open Source Agent Templates for Atlas Agent Engine
MongoDB Agents is a collection of open source templates for Atlas Agent Engine that handle credential handling, access scoping, and tool orchestration. It includes two templates: Atlas Explorer for conversational workflows and Atlas Query Insights for slow-query reporting.
Atlas Stream Processing: cron schedule in $source stage
Adds support for a cron schedule in the $source stage.
Atlas Stream Processing vertical autoscaling
Adds support for vertical autoscaling of stream processing.
Atlas Stream Processing adds Google Cloud us-west1 and three Azure regions
Adds us-west1 in Google Cloud and northeurope, eastasia, and southeastasia in Azure.
Change stream initial sync handles mixed-type _id values
Initial sync can copy collections whose _id values span multiple BSON types, such as ObjectId, string, numeric, date, and UUID.
$iceberg stage writes to S3 with s3:// scheme
The $iceberg stage writes to AWS S3 using s3:// instead of s3a://, increasing compatibility with external query engines.
Private Link support for $externalFunction stage
Adds Private Link support for the $externalFunction aggregation stage, including AWS Lambda Private Link connections.
Parallelism in $externalFunction stage
Adds support for parallelism in the $externalFunction aggregation stage.