Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.
Monitor and control AI actions with safety measures and an audit trail, without changing any code.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeRuntime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.
Aegis has 343 stars on GitHub. It has been forked 38 times. Aegis is written mainly in TypeScript. It has been in active development since 2026. Aegis is available under the MIT license. Its main topics are ai-agents, ai-safety, anthropic, audit-trail.
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.
Aegis is an open-source project. It is released under the MIT license.
Yes. Aegis is free and open source — you can use, modify and self-host it.
Aegis is available under the MIT license.
Aegis is written mainly in TypeScript.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/justin0504-aegis.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.