AWS updates AgentCore runtime: sessions start up to 15 times faster
Understand this story
AWS has updated the Amazon Bedrock AgentCore runtime, with each session still running in an isolated Firecracker MicroVM. AWS says the new version starts sessions up to 15 times faster, with startup time under 2 seconds, regardless of image size and concurrency; per-session compute is expanded to 4 times that of the previous version, up to 8 vCPU and 32 GB, supports container images up to 10 GB, and improves runtime efficiency by up to 68%. The new version is available in AWS Regions in North America, South America, Europe, and Asia Pacific. In a follow-up technical blog post, AWS explains that the new architecture corresponds to platformVersion "V2": a snapshot is built once at creation or update time, new sessions restore directly from the snapshot, and unused memory is reclaimed. AWS says that for most agents, switching to V2 is sufficient; the V2 runtime also supports build hooks. For long-running agents, AWS offers committed baseline pricing: a memory baseline is set per session and serves as the minimum billable amount, with on-demand bursting up to 4 times the baseline. AWS also says that by re:Invent it will bind each session to a separate storage folder through session-tag credentials.
AI overview based on source reports · Updated 15 hr ago
Developments
2 developments
- Nov 14 06:02 · 1 reportsIntroducing AgentCore runtime V2 session startup optimization methodsAWS Machine Learning Blog：Architecture patterns for fast session startup on Amazon Bedrock AgentCore runtime
- Nov 13 01:59 · 1 reportsLaunching the next-generation AgentCore runtimeAWS Machine Learning Blog：Run agents securely and efficiently with the next generation AgentCore runtime
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogArchitecture patterns for fast session startup on Amazon Bedrock AgentCore runtime
Amazon Bedrock AgentCore runtime's platformVersion "V2" snapshots a prepared container once at create or update time and restores it for each new session, making session starts faster and more consistent. The post explains how V2 starts sessions, how to measure session start time with CloudWatch metrics like OverheadLatency, and four patterns: moving initialization before app.run(), using build hooks for files the process can't hold, and pre-warming sessions on user engagement for sub-second starts.
- AWS Machine Learning BlogFeaturedRun agents securely and efficiently with the next generation AgentCore runtime
AWS announced updates to the Amazon Bedrock AgentCore runtime that keep each session in its own hardware-isolated Firecracker MicroVM while starting sessions up to 15x faster, scaling to 4x more compute (up to 8 vCPUs and 32 GB, with container images up to 10 GB), and running up to 68% more efficiently. The runtime now reclaims memory within minutes of release and scales idle agents to zero, and agents can dynamically mount and save work to a filesystem such as an Amazon S3 bucket with FUSE support so data stays inside the trust boundary. The next generation runtime is available today in AWS Regions across North America, South America, Europe, and Asia Pacific.
Activity for this story
- Current comparable activity
- 7
- Peak comparable activity
- 10Nov 13 03:00
- Change in the past 24 hours
- +12%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.