AI Security AI tools
Guardrails, firewalls and secret exposure checks for AI agents. See the best-of list.
Use cases
See which secrets a coding agent can reach
Heldkeys lists the credentials an AI agent can access on a machine or in CI; aws-safebox is a proof-of-concept command guardrail for AWS work.
Tools (4)
AAegis
Says it is a machine-wide firewall for AI tools that applies guardrails to every request and response.
AAegisKernel
Open-source project that says it is a zero-trust, deterministic security runtime for autonomous AI agents.
Aaws-safebox
Proof of concept: local guardrails that allow or block commands an AI agent runs during AWS infrastructure work; the author says it is not a hardened sandbox.
HHeldkeys
Open-source tool that lists the credentials an AI agent can reach on a laptop, sandbox or CI and flags risky agent steps in GitHub workflows.
Get new tools and use cases by email
A free email, weekly, every Friday, with newly added AI tools and agent use cases. Unsubscribe anytime. Plus our free AI tools starter kit for small businesses (PDF).