Google releases an open source platform for AI agents
Google has announced the release of their open source AX platform for running large scale AI Agents. You can find the code here on Github under the Apache 2.0 license. This platform self hosts Git and MCP servers based off of simple textual specifications and can handle billions of tasks.
Google recently released an open source implementation of their AX platform which allows you to run large scale AI Agents. You can check out the code on Github here under the Apache 2.0 license. It allows you to self host your own Git/MCP servers using simple textual descriptions and can manage billions of tasks. Their AX platform is a runtime for AI agents. They say they’ve been able to scale it to billions of tasks. Idle agents can be restarted almost instantly.
This isn’t really something that most container orchestrators were built for. An agent might be idle for hours at a time, but then suddenly they all start hogging resources. If they really can create environments from text descriptions, that will be very useful for me when building new pipelines. For now, it’s just some documentation, but I’ll have to give it a shot because it’s from Google Research.
Source: agentexecutor.io
Free course
Stop reading about AI — start building with it
The free Claude Code course: your first site, tool or game — no coding. No upsells, no cross-sells — nothing to buy here.
Start free →▌ Related guides
Author
Evgenii Arsentev
PhD · Founder & CEO, Dad4Kids
Articles · Latest articles