Agent Control
ActiveDescription
Centralized agent control plane for governing runtime agent behavior at scale. Configurable, extensible, and production-ready across multiple agent frameworks.
Related Projects
Reins
412 · Python
Stop AI agents from doing things you did not ask for. Behavior monitoring and permission control ensure agents operate only within authorized bounds.
agent-safetybehavior-controlguardrails +2
SCAM
105 · Python
Security Comprehension Awareness Measure by 1Password. An open-source benchmark testing AI agents' security awareness during realistic, multi-turn workplace tasks.
security-benchmarkagent-safetyworkplace +2
SecureClaw
337 · TypeScript
An OWASP-aligned security plugin for AI agents, providing comprehensive security assessment and protection including prompt injection defense and access control.
owaspsecurityplugin +2
AgentFence
54 · Python
An open-source platform for automatically testing AI agent security. Identifies vulnerabilities such as prompt injection, secret leakage, and system instruction exposure.
security-testingvulnerability-scannerprompt-injection +2