Every agent runs inside a microVM secured by Google's Titanium chip, according to the company. When an agent is idle, its VM pauses automatically so the underlying machine can serve other workloads, and shared memory between VMs lowers the cost of running each one.
Google has also open-sourced Agent Substrate, a Kubernetes runtime that it says can fit ten times as many agents on a single server. In a test with 200,000 agents, suspend and resume took less than 500 milliseconds, Google reports.
On the oversight side, Google is adding token tracking, model routing and support for third-party identity providers such as Ping Identity and SailPoint. These controls are set to extend to Cloud Run, GKE and managed endpoints.
Why it matters if you build agents
Developers running many short-lived agents may be able to suspend idle ones without paying for a dedicated machine for each. Per-agent isolation could also simplify keeping the data of different users or tenants apart.
Before relying on it, check when the preview opens and whether the token tracking and identity controls cover the hosting targets you use.
Get stories like this every weekday
One short email with the day's agent tooling news.