Run agents securely and efficiently with the next generation AgentCore runtime
AI agents now run multi-step workloads for hours and act on behalf of users, raising the bar for secure, scalable agent compute. Learn how the next generation of Amazon Bedrock AgentCore runtime delivers hardware-isolated sessions with faster starts, more compute, usage-based billing, and isolation that now extends to your data.
First seen by Oriel on .
AI summary
Amazon Bedrock AgentCore’s next-generation managed runtime provides hardware-isolated agent sessions with faster startup, larger workloads, usage-based resource efficiency, and storage within the security boundary.
- Each session runs in its own hardware-isolated Firecracker MicroVM with separate identity, policy, and audit trail.
- Sessions support up to 8 vCPUs, 32 GB, and 10 GB container images, starting in under 2 seconds regardless of image size or concurrency.
- Released memory is reclaimed within minutes, idle agents scale to zero, and multi-turn sessions can consume up to 68% less memory.
- Agents can dynamically mount and save work using filesystem support, including Amazon S3 with FUSE, while data remains inside the governed trust boundary.
- The runtime is available today across AWS Regions in North America, South America, Europe, and Asia Pacific.
#ai agents #aws #firecracker #sandboxing
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| AWS Machine Learning Blog | 5460e26111aeb2444e58fb192084957f53ebb300 | https://aws.amazon.com/blogs/machine-learning/run-agents-securely-and-efficiently-with-the-next-generation-agentcore-runtime/ Read discussion |