ZeroClaw: What's Been Going On
Hey everyone,
We're moving fast and learning as we go.
Recent Incident
Over the past few days, a maintainer used aggressive AI automation to review and merge PRs:
- Merges went through that shouldn't have.
- In the process of trying to undo the damage, the maintainer's GitHub account was flagged, which triggered enforcement actions on the ZeroClaw org itself.
- That maintainer has been removed from the project.
Community Contributions Come First
There's a pattern where maintainers implement fixes to issues without first checking whether a community PR already addresses it:
- This leads to wasted contributor time, which we understand is frustrating.
- We're fixing this going forward — maintainers will be expected to review the open PR queue first. Community contributions come first.
What We're Doing
Stabilization comes first
We're auditing recent merges, reverting what needs reverting, and making sure master is in a clean, reliable state.
If you've hit weird breakage recently, please let us know — we're looking at it.
Adoption of open-source agentic engineering practices
We're getting smarter about how we move fast.
LLM review will be advisory. A human maintainer must approve and merge.
We want ZeroClaw to be a model for how open-source projects integrate AI tooling into their workflows responsibly.
Tighter merge access
We're moving to a tiered model:
- Contributors submit
- Reviewers approve
- A small trusted group can merge into master
- Branch protections are being tightened accordingly
Weekly Roadmap Review
Starting immediately, I'll be running a weekly roadmap review to keep ZeroClaw aligned with its original vision as an open, vendor-neutral AI agent runtime. 8PM EST on Thursday on Discord.
These will be public and I want your input:
- How do you use ZeroClaw?
- What's working?
- What's not?
- What do you need?
If you have questions, feedback, or want to get involved in the new review process, drop a comment or reach out directly.
— JordanTheJet
CEO, ZeroClaw Labs