#DevGuide
The new AgentCore Runtime is now available in Amazon Bedrock AgentCore

Today, AWS announces the availability of the next generation of https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agents-tools-runtime.html, the serverless microVM compute within Amazon Bedroc...

#AWS #AmazonBedrock
The new AgentCore Runtime is now available in Amazon Bedrock AgentCore
Today, AWS announces the availability of the next generation of https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agents-tools-runtime.html, the serverless microVM compute within Amazon Bedrock AgentCore. The new Runtime delivers elastic memory management that reclaims unused memory throughout the session so you pay for actual usage rather than the peak, and consistent cold start times regardless of container image size or concurrency. You get the serverless model you already rely on: no pre-provisioning, scale to zero, hardware-enforced session isolation, and pay only for what you use - now with lower costs and faster starts. With the new Runtime, each session starts with a small, efficient memory profile. Additional memory is allocated on demand as the workload needs it, and memory that is no longer actively used is reclaimed rather than held until the session ends. For cold starts, the new Runtime prepares the agent environment once and snapshots it. Every new instance restores from that snapshot instead of repeating the full startup sequence, keeping start times consistent regardless of image size. In testing, the new Runtime delivered a P75 cold start of 1.9 to 2.0 seconds for container images from 200 MB to 2 GB, compared to 5.4–30 seconds with V1. The new AgentCore Runtime is available in the following regions: us-east-1, us-east-2, us-west-2, eu-west-1, and ap-northeast-1. To get started, set platformVersion to V2 when creating or updating a runtime. To learn more, visit the https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-how-it-works.html#runtime-platform-versions or the https://aws.amazon.com/blogs/machine-learning/the-new-agentcore-runtime-elastic-optimized-and-consistently-fast-starts/. For pricing details, visit https://aws.amazon.com/bedrock/agentcore/pricing/.
aws.amazon.com
September 18, 2026 at 4:05 PM
Amazon Bedrock AgentCore Identity now offers a managed consent portal

https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/identity-overview.html now offers a managed consent portal that eliminates the need for custom OAuth callback infrastructure when connecting ag...

#AWS #AmazonBedrock
Amazon Bedrock AgentCore Identity now offers a managed consent portal
https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/identity-overview.html now offers a managed consent portal that eliminates the need for custom OAuth callback infrastructure when connecting agents to third-party tools and services. Developers using AgentCore Gateway to connect agents with services such as GitHub, Salesforce, and Slack previously had to build, host, and maintain custom OAuth callback infrastructure to complete OAuth 2.0 three-legged authorization (3LO) flows. The new managed consent portal eliminates this undifferentiated heavy lifting for agent developers and platform administrators. Each AgentCore Gateway receives its own managed consent portal with a dedicated hosted web client and credential provider list. Platform admins can share a portal URL with their team before sessions begin, granting consent for agents to call external tools on their behalf. End users can view their connection status at any time through a self-service interface without contacting an administrator. Developers using agent IDE-based clients, which cannot natively present OAuth consent URLs or handle post-consent session binding, can now use the managed consent portal as a dedicated authorization surface for these workflows. This feature is available in all commercial regions where Bedrock AgentCore Identity is available. To learn more, visit the http://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/identity-consent-portal.html.
aws.amazon.com
September 3, 2026 at 10:05 PM
🔒🐍 Coming soon, Python 3.15 release candidate 1! The 3.15 branch is now locked until 3.15.0 final in October.
discuss.python.org/t/the-3-15-b...

Also coming soon: Python 3.13.15 and 3.14.7.
hugovk.dev/next-release/
#Python #Python315 #Python314 #Python314 #release
The 3.15 branch is locked for RC1
The 3.15 branch is now locked for all (except release managers and admins) until the 3.15.0 final release (scheduled for 2026-10-01). Reminder from the devguide: A branch preparing for an RC…
discuss.python.org
August 4, 2026 at 8:56 AM
Amazon Bedrock AgentCore increases default runtime quota limits

Amazon Bedrock AgentCore has increased the default runtime quota limits, giving customers greater capacity to scale their agent-based workloads. AgentCore is the platform for developers to build, connect, and op...

#AWS #AmazonBedrock
Amazon Bedrock AgentCore increases default runtime quota limits
Amazon Bedrock AgentCore has increased the default runtime quota limits, giving customers greater capacity to scale their agent-based workloads. AgentCore is the platform for developers to build, connect, and optimize AI agents. The new default limits support up to 5,000 active concurrent sessions in US East (N. Virginia) and US West (Oregon), and 2,500 in all other supported Regions. All https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-regions.html is available now support 200 agent interactions per second and 25 new sessions created per second. This means customers can run more AI agents simultaneously while handling high-throughput workloads out of the box. To learn more, visit the https://aws.amazon.com/bedrock/agentcore/ or see the https://docs.aws.amazon.com/bedrock-agentcore/. For all quota limits, see the https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/bedrock-agentcore-limits.html.  
aws.amazon.com
July 1, 2026 at 10:05 PM
I'm biased because I helped write part of it (and @balbi.sh has continued adding even more info!), but I think the `embassy-mcxa`'s DEVGUIDE is probably one of the better references now for "how embassy HALs work and how to write a good one", if that's what you're in to.

github.com/embassy-rs/e...
github.com
June 19, 2026 at 10:20 PM
You’re the face of the devguide now ;-)
June 8, 2026 at 6:21 PM
AWS Step Functions adds AgentCore-powered agentic reasoning step

AWS Step Functions now enables you to add AI agent reasoning steps to your workflow through an optimized integration with the managed harness (currently in preview) in Amazon Bedrock AgentCore. https://aws.a...

#AWS #AwsStepFunctions
AWS Step Functions adds AgentCore-powered agentic reasoning step
AWS Step Functions now enables you to add AI agent reasoning steps to your workflow through an optimized integration with the managed harness (currently in preview) in Amazon Bedrock AgentCore. https://aws.amazon.com/step-functions/ is a visual workflow service that orchestrates AWS services with built-in error handling, parallel execution, and human approval steps. The AgentCore https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness.html lets you declare an agent through configuration where you specify the model, tools, and behavior. AgentCore provides the managed environment that runs the agent loop end-to-end.   With this integration, you can automate reasoning tasks in your workflow such as classifying a document or extracting elements from an unstructured form. You can run multiple agents in parallel or in sequence at different decision points in a single workflow and add human approval before critical actions. The workflow execution history shows agent input, output, token usage, and duration with links to agent turn details in Amazon CloudWatch, so you can trace and audit every agent decision. You can reuse an existing harness or create a new one directly from the Workflow Studio, the Step Functions visual builder. With per-invocation overrides such as the model, system prompt, and tools, you can adapt the agent to each workflow context without duplicating configurations. Agent context can be persisted across invocations using a session ID that works within or across workflow executions.   The harness integration is available in the following AWS Regions where the AgentCore harness preview is available: US East (N. Virginia), US West (Oregon), Europe (Frankfurt), and Asia Pacific (Sydney). Standard Step Functions pricing applies for workflow execution with no additional integration charges, and standard Amazon Bedrock and AgentCore pricing applies for model inference and associated AgentCore resources.   To learn more about adding agentic reasoning to your workflows, visit AWS Step Functions https://docs.aws.amazon.com/step-functions/latest/dg/connect-bedrockagentcore.html. 
aws.amazon.com
June 3, 2026 at 8:05 PM