Google's AX orchestrator scales to billions of agent tasks per cluster
Google's Open Agentic Orchestrator
AX is an open declarative control plane from Google for running agentic workloads at massive scale. Built on the Agent Substrate runtime, it sandboxes tasks, wires workspaces, fences networks, and supports billions of concurrent sessions per cluster with sub-second suspend and resume. Four primitives handle state, isolation, API calls, and cost control, while generative workspaces let you describe an environment in plain English and have it prepared automatically.
Agents are a new kind of workload. They are neither microservices nor batch jobs. They accumulate state, need strict isolation, call out to model APIs and tool servers, and can burn money in a loop if nobody is watching.
- sigbottle
Could someone explain to me what the general workflow is now that people are converging to? I haven't really been catching up with the AI ecosystem but I was looking into agent sandboxes and VM's recently and there's a ton of these startups and tools now. Is giving the agent a temporary scratchbox really that valuable?
I've been still just like, making VM's with proxmox, then putting my agent in the machine and letting it run free (with my dotfiles setup script making dev env pretty much free, though I could also just make a VM snapshot). What's wrong with that? Is that not the scalable solution for enterprise rn?
- mcoliver
I have been happy with Google's Antigravity harness and Jules so looking forward to playing with this. Thanks for sharing. Simultaneously I am looking to also revisit local offline models.
While I feel like I have a decent understanding of the model landscape I'm feeling a bit lost at which agentic harness to leverage for local models. Hermes, Cline, Aider, Qwen Code, Goose, Pi, OpenCode, something else? I live in the terminal so Desktop UX is a bonus but not a must have.
Can I modify the antigravity settings/program to point to a local model? Where should I spend my energy?
- dmix
> Task declares the container image and command, compute requests and limits, environment variables [...] Declares listeners the task exposes and an egress allowlist of hosts and ports the sandbox may reach. Use it to restrict an agent to, say, your LLM provider and your Git host.
I'm planning to buy a whole linux mini-PC to run my agents/code servers for more isolation. Codex/Claude Code let you run prompts on code over ssh (same with most IDEs) even on the desktop apps.
I wonder if that's going to be the new standard practice. You get a work laptop and an isolated agent box.
Running access control and network whitelists is always a maintenance challenge and it's easy to make mistakes.
- weedfroglozenge
Nobody has a use for this, and anybody who can look at this website and work out what it's for is kidding themselves. Even the demo gif playing just has them pausing a task and resuming the task.
- Mond_
The reality with releases like this is that I'm 90% sure most Google bigwigs have never heard of it, and it's misleading to label it as "Google's" in the title.
Yes, it was developed by Google employees, that does not imply it has the full backing of Google, or Deepmind, or GCP. Notably, the website doesn't seem to claim this either.
- aleksandrm
I looked at the website, and I still don't understand the purpose.
- pianopatrick
I can understand why it was chosen, but I'm not a fan of writing a bunch of yaml.
- dilyevsky
Interesting, we had developed a very similar framework for our internal agents: https://github.com/apoxy-dev/clrk For us main use-case was intercepting all network I/O including LLM providers, HTTP, and random TCP/UDP calls