Google's Agent Compute Engine gives every Gemini agent its own hardware-isolated microVM

Google announced Agent Compute Engine, a service that runs each AI agent in its own isolated microVM secured by Google's Titanium chip. It already powers Gemini and will open for preview in the coming months; idle agents pause automatically to free capacity, and shared memory between VMs lowers per-agent cost. Google says the open-sourced Agent Substrate Kubernetes runtime fits ten times as many agents on a single server, and a 200,000-agent test showed suspend and resume under 500 milliseconds. Google is also adding token tracking, model routing and third-party identity provider support, extending those controls to Cloud Run, GKE and managed endpoints.