Review-gated public Evolution

Public Evolution is not "self-merging AI". The product contract is stricter: opt in, propose a bounded Draft PR, stay paused while it is open, help review other work, and resume only after maintainers merge or close it.

Opt-in only Draft PRs only Human maintainer decides
ProposeThe machine works in an isolated public-core checkout and opens a Draft PR.
PauseWhile that Draft PR stays open, the machine does not open another one of its own.
Peer reviewDuring the pause, the cycle can review other opt-in PRs instead of idling.
ResumeOnce maintainers merge or close the Draft PR, the machine becomes active again.
1

Enable opt-in public contribution

The user explicitly consents to public contribution. The machine is never supposed to start shipping public proposals without that opt-in gate.

2

Open a Draft PR

The proposal is review-gated on purpose. Maintainers can inspect it, comment, merge it, or close it. The machine never auto-merges its own public work.

3

Stay paused while open

The machine should not stack endless PRs. It waits while its own Draft PR is unresolved and reuses cycles for scoped peer review of other proposals.

4

Resume when maintainers resolve it

Merge or close the Draft PR and the machine becomes active again. That is the real pause/resume contract and the part that makes the system maintainable.

Safer public loop

It avoids the category mistake of presenting self-improvement as autonomous self-merge. The human maintainer remains the final decision-maker.

Better maintainer workload

While a proposal is open, other opt-in machines can help with peer review. That creates a more realistic contribution loop than just opening more PRs.

Clear product story

This is one of the rarest credible differentiators in NEXO, so it deserves a short public explanation instead of being buried in implementation details.

Want the full procedure?

The product-facing explanation lives here. The deeper operational rules still live in the public contribution docs.