All tech news

AIInfoQ · 12 h ago

Google Announces Agent Compute Engine for Secure AI Agent Execution

Photo: InfoQ

Google recently announced Agent Compute Engine, a managed service that runs AI agents in isolated microVMs, with checkpointing capabilities to suspend and resume execution environments. The design keeps credentials, API keys, and OAuth refresh tokens outside the agent sandbox, using an external Agent Gateway to authenticate requests and inject the required secrets. Agent Compute Engine achieves this by using copy-on-write memory sharing to run multiple agents on a single operating system template, and pausing idle microVMs via fast checkpoint and restore.

The orchestration harness (the brain) runs completely outside the execution sandbox (the hands), helping ensure that untrusted guest environments only execute explicit commands dispatched by the harness and stream output back.

Excerpt from InfoQ, in their own words. Bonzai did not write this story; the full version is on the publisher’s site.