I'd evaluated both Google's Agent Substrate (that underlies Ax) and their Scion project. I really enjoy how Scion operates with existing tools really well. Ax/Agent Substrate is much more a greenfield independent effort, it's own thing.
I think Scion has so much more mature a disosition: you could write OpenCode plugins that enhance the runner, and use that locally, and use it in Scion. With Ax/Agent Substrate, you are opting in to a pretty huge stack that is just Agent Substrate, that is their runners, their harness, their substrate. I do think their actor model is pretty neat! It's neat having the agent have such primacy! But it feels so much less integrative, is such it's own thing. Scion, to me, is much more interesting an effort, that similarly helps scale out agentic workloads.
thanks for the kind comments (lead Scion architect here), Scion is still very much meant for teams of people to interact with teams of agents. it is not just about scheduling agents on infrastructure. it’s been getting some new UX improvements:
<a href="https://youtu.be/1WYsoSXt9QQ" rel="nofollow">https://youtu.be/1WYsoSXt9QQ
jauntywundrkind · · focus · HN ↗
I think Scion has so much more mature a disosition: you could write OpenCode plugins that enhance the runner, and use that locally, and use it in Scion. With Ax/Agent Substrate, you are opting in to a pretty huge stack that is just Agent Substrate, that is their runners, their harness, their substrate. I do think their actor model is pretty neat! It's neat having the agent have such primacy! But it feels so much less integrative, is such it's own thing. Scion, to me, is much more interesting an effort, that similarly helps scale out agentic workloads.
<a href="https://github.com/googlecloudplatform/scion" rel="nofollow">https://github.com/googlecloudplatform/scion
ptone · · focus · HN ↗