dominis

Sorry, English is my second language. When I wrote "won't work", probably what I meant was: won't scale.

I am certain we are going to end up using these tools like we do with CI in the near future. With this, you'll get full observability, RBAC, sandboxing, and reproducible benchmarking.

I assume as an enterprise you will want all of these when you spend a big chunk of your budget on tokens.

If you think about the evolution of AI coding, companies (who will eventually pay for these tools) will realize they want to run the coding tasks in a remote, controlled environment. Every engineer typing on their machine and burning tokens (money) won't work in an enterprise setting.

I wouldn’t be surprised if in most cases it’s $100 in $1 out.

on individual level for basic things I found hooks pretty good, you can block tool executions easily.

I think here the question will be how to scale rules on team level.

Obviously sandboxing will be needed if we want proper gates.

<3

I'm not familiar with this project, just checked their GitHub Readme and if I understand correctly they block what you want them to block. Sinkzone does the opposite, it allows what you want to allow, and blocks everything else.

I'm planning to address the issue for phones as well in the future.

You can configure your upstream resolvers in the config, so I think Sinkzone can be placed in front of your VPN's resolver. I never tested this to be honest.

It's on my list :)

Hey Eszpee, Thanks for checking Sinkzone out. I'm thinking about building custom schedules in the next iteration, that would support some basic pomodoro style scheduling for sure.

I wanted to build my tool because eventually I want to support multi-tenancy. Custom allowlists and schedules for all family members.