← Ajin Baby's projects
Pythonagentsaidatasetevaluationguardrailsincident-management
Public AI-agent production failures as a versioned, replayable regression corpus — each with a runnable reproduction and a CI gate that fails when your guardrails stop containing them. Code Apache 2.0, data CC BY 4.0.
More from members
All projectsSee what other members are building and what each project is looking for.
Comments · 0