guardana

Guardana is an open-source tool for AI security verification, scanning model artifacts, probing live endpoints, and analyzing recorded agent traces. It produces reproducible evidence and a measured verdict, enabling comparison of releases against accepted baselines for continuous security assurance.

guardana sits in the Security & Safety category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Static and offline verification of model and code artifacts. A representative use case is Integrate into CI/CD pipelines as a security gate. The listed license is Apache-2.0. GitHub stars are currently 252. Relevant tags include AI Security, LLM Security.