AWS AgentCore runtime adds faster sessions and scale-to-zero billing
Start here
AWS updated the Amazon Bedrock AgentCore runtime, its managed compute layer for agents. Sessions now start in under 2 seconds regardless of container image size or concurrency, and each session can scale to 4x the previous compute, up to 8 vCPUs and 32 GB, with container images up to 10 GB. AWS says sessions also run up to 68% more efficiently, and each stays in its own hardware-isolated Firecracker MicroVM. Idle agents scale to zero, and agents can mount and save work to a filesystem such as an Amazon S3 bucket via FUSE, keeping data inside the trust boundary. For always-on agents, committed baseline pricing sets a per-session memory minimum that can burst up to four times on demand. The next-generation runtime is available in AWS Regions across North America, South America, Europe and Asia Pacific; AWS says per-session storage scoping via session-labeled credentials is planned by re:Invent.
Generated from reports · updated 12 h ago
Report timeline
Follow the reports to see the event from different sides.
- AWS Machine Learning BlogPicksAWS updates AgentCore runtime with 15x faster session starts and 4x more compute
AWS announced updates to Amazon Bedrock AgentCore runtime, its managed compute layer for agents, with sessions now starting 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, while each session stays in its own hardware-isolated Firecracker MicroVM. Sessions start in under 2 seconds regardless of image size or concurrency, idle agents scale to zero, and agents can mount and save work to a filesystem such as an Amazon S3 bucket with FUSE support so data stays inside the trust boundary. The runtime is available today in AWS Regions across North America, South America, Europe, and Asia Pacific.
Heat for this event
Not enough continuous observations yet to draw a trend.