Axiom

We started working on Axiom after noticing the same pattern over and over while building LLM systems during internships and security work. Once models touched real users and real inputs, issues like prompt injection, data leakage, and unintended behavior showed up almost immediately. These were not edge cases. They were part of normal usage. Axiom focuses on securing how models are actually used in production. We are excited to share what we have built so far and are actively learning from early users. If you are deploying LLMs today, we would love your feedback.