ai-agents-security

Open repos and models their makers tagged ai-agents-security, most starred first. The same for everyone.

AI on my own machineRepo

Preventing-AI-Hallucinations-and-Unauthorized-Actions-Runnable-Reference-Implementation

Runnable Python reference implementation ensuring AI hallucinations and unauthorized agent actions remain non-effective until policy, evidence, scope, and safety checks authorize execution through a one-time Execution Handle and Finality Sink. Includes 74 passing security tests and latency benchmarks.

  • 0
  • Python
  • 2 mo ago
sangmdasTake it
Search GitHub and Hugging Face for ai-agents-security

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

ai-agents-security: open source repos and models on Take My Repo