Could agent-zero / OpenClaw runs become playable Story artifacts? #1795
sunfishloop
started this conversation in
Show and tell
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Hi agent-zero community. I noticed the Show and tell threads around OpenClaw-based personal agent frameworks, and this seems like a good fit for something I’ve been working on: turning actual agent run traces into sanitized, playable artifacts instead of asking maintainers to read raw logs.
The concrete GitHub Action is here: https://github.com/marketplace/actions/publish-agent-story
Why I think it may fit agent-zero / OpenClaw users specifically: many demos are not just final outputs; the interesting part is the loop of goal, tool choice, observation, recovery, and final result. A Story can preserve that sequence for a demo, bug report, or release note while stripping private chain-of-thought, credentials, and internal logs.
Low-pressure CTA: would a minimal opt-in workflow PR be useful here, gated behind a manual trigger, that publishes one sanitized agent-zero/OpenClaw run as a SunfishLoop Story? If yes, I can prepare the smallest version and keep it non-invasive.
All reactions