Show HN: Kybernis – Prevent AI agents from executing the same action twice

Sobre

AI agents increasingly execute real system actions: issuing refunds, modifying databases, deploying infrastructure, calling external APIs.<p>Because agents retry steps, re-plan tasks, and run asynchronously, the same action can sometimes execute more than once.<p>In production systems this can cause duplicate payouts, repeated mutations, or inconsistent state.<p>Kybernis is a reliability layer that sits at the execution boundary of agent systems.<p>When an agent calls a tool:<p>1. execution inte