agent-safety-frameworks

Open repos and models their makers tagged agent-safety-frameworks, most starred first. The same for everyone.

AI agentsRepo

OpenART

OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.

  • 277
  • Python
  • AGPL-3.0
  • 3 d ago
AI45LabTake it
Search GitHub and Hugging Face for agent-safety-frameworks

Get , open it once and sign in. Then come back here and press the button again.