ptone
Re:Google's Open Agentic Orchestrator
on Tuesday September 22, 2026 @12:26AM (#49796788)
it’s true. Google rarely has just one of anything
Re:Google's Open Agentic Orchestrator
on Tuesday September 22, 2026 @12:02AM (#49796661)
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:
https://youtu.be/1WYsoSXt9QQ
Re:Google Open Sources Experimental Agent Orchestration Testbed Scion
on Tuesday April 07, 2026 @06:42PM (#47682287)
[primary author and architect of scion here] The reason this is a testbed is because this is a new and emerging area of replacing things like codified graphs in tools like langraph with pure agent instruction where agents manage agents with a lot more autonomy. These patterns are not well explored, and are not ready for production in most cases. The goal of a testbed is to have an easy and quick way to try out N of these patterns.
Re:Google Open Sources Experimental Agent Orchestration Testbed Scion
on Tuesday April 07, 2026 @04:35PM (#47681010)
[primary author and architect of scion here] Actually - there are two other big parts: a CLI and a control plane
Re:Google Open Sources Experimental Agent Orchestration Testbed Scion
on Tuesday April 07, 2026 @04:34PM (#47681007)
This runs stock Claude Code in containers, should be completely fine for TOS
Re:Google Open Sources Experimental Agent Orchestration Testbed Scion
on Tuesday April 07, 2026 @04:32PM (#47680976)
[primary author and architect of scion here] The missing features are mostly by design - this is closer to what the gastown plans as "gascity" - bring your own orchestration characters and definition.
If you look at this orchestration example
https://github.com/ptone/scion-athenaeum
its just markdown - Scion is the game engine
(a port of gastown to run on scion is in progress)
Re:Google Open Sources Experimental Agent Orchestration Testbed Scion
on Tuesday April 07, 2026 @04:29PM (#47680940)
[primary author and architect of scion here] Part of this will be pushing that cognitive overhead increasingly onto agents. By how much and when is what Scion is here to explore.
Re:Google Open Sources Experimental Agent Orchestration Testbed Scion
on Tuesday April 07, 2026 @04:27PM (#47680925)
[primary author and architect of scion here]
There are several layers of state and telemetry - first is provided by the hook system available in most harnesses, then for those that provide OpenTelemetry -that is normalized and forwarded raw (preserving both) to a cloud collector. Finally - some activities are "self reported" by agents using a built-in toolset that can be reflected in the control plane
Re:Gemini CLI
on Thursday June 26, 2025 @09:23PM (#44393022)
Been working on this, and should now be resolved https://github.com/google-gemini/gemini-cli/discussions/2064
Re:Gemini CLI
on Thursday June 26, 2025 @09:23PM (#44393020)
Try it out with 0.1.5 https://github.com/google-gemini/gemini-cli/discussions/2064
Re:Gemini CLI
on Thursday June 26, 2025 @09:22PM (#44393018)
This should be resolved: https://github.com/google-gemini/gemini-cli/discussions/2064
Re:Gemini CLI
on Thursday June 26, 2025 @09:21PM (#44393014)
Things should be better now: https://github.com/google-gemini/gemini-cli/discussions/2064