Show HN: Deterministic AI Agents Guardrail

Category: devtools

Tags: ai-agents, infrastructure, safety, policy-enforcement, aws

Score: 6.5/10 (Innovation: 6, Technical: 6, Documentation: 8, Utility: 6)

AWS SafeBox is a deterministic policy layer that intercepts commands from AI agents to infrastructure tools like Terraform and the AWS CLI, blocking known destructive operations such as 'terraform destroy' or 'aws ec2 terminate-instances'. It uses TOML-based rules and a fail-closed approach, providing a simple but effective guardrail to prevent accidental infrastructure damage.

Target audience: devops, backend devs, ai engineers

Repository: https://github.com/aws-safebox/aws-safebox · Python · NOASSERTION · 2 stars

View on Hacker News