Google launches cloud service for running Gemini AI agents
The new Agent Compute Engine pauses idle agents and restarts them on demand, aiming to reduce costs for companies scaling AI.
By Standard Topic. AI-generated from the reporting listed under Coverage. Published . Updated .
This story is no longer being updated. It reflects reporting up to .
What happened
Google announced Agent Compute Engine on Thursday at the Linux Foundation's AGNTCon+MCPCon event in San Jose. The service gives each agent its own hardware-isolated micro virtual machine and can suspend inactive agents, then restore them on demand with their execution state preserved. It will reach Google Cloud users in preview later this year.
Why it matters
Google says idle infrastructure costs could become a major barrier as enterprises scale up AI agents. The service is aimed at addressing that challenge.
Timeline
- Oct 22: Google announces Agent Compute Engine at the AGNTCon+MCPCon event in San Jose.
- Later this year: Agent Compute Engine becomes available in preview to Google Cloud users.
Coverage
- Google targets AI agents’ idle-time costs with new compute service (infoworld.com)
- Google Cloud introduces Agent Compute Engine to host AI agents (siliconangle.com)
- Google's Agent Compute Engine gives every Gemini agent its own hardware-isolated micro virtual machine (the-decoder.com)
- Google turns the infrastructure behind Gemini’s agents into a cloud service (thenewstack.io)
- Agent Compute Engine deep dive (cloud.google.com)
- Google for Developers Blog - News about Web, Mobile, AI and Cloud (developers.googleblog.com)
More from Technology & AI
- China puts humanoid robots to work serving food and sorting parcels
- Newsom proposes sweeping AI safety rules for Washington
- Google releases Gemini 4 Neon AI model with million-token context
- Microsoft and Intel widen their cloud chip partnership
- Google DeepMind rolls out Genie 4 to select subscribers
- AI helped AMD shorten chip design work, OpenAI says