Show HN: An open source safety layer for AI agent actions (github.com)

Please let me know what you think of it. I feel like in the chaos of everyone using AI agents, people are actually neglecting how much harm consequential actions by those agents can cause, so my friend and I created this.

I am available all the time for any questions you have. If you need help, take a look at the documentation here: https://ctrlrun.dev/docs/get-started/quickstart

You can also star the repo, which motivates me and my friend to keep working on this project.

Thanks, HN :)

[dead]