I'm using Catnip (https://github.com/wandb/catnip). It runs Claude Code in YOLO mode inside a Docker container, and also manages multiple Claude instances running in Git worktrees. I'm pretty happy with it but would be happier if it addressed limiting network access to guard against exfiltration.
Tangential: a friend of mine growing up refused to read Ayn Rand, because he said that everyone he knew that had read her books turned into assholes, and he didn't want to become an asshole too.
I've read enough to find this statement to be largely correct. I found myself fully aware of the kinds of people who admired the thought patterns they wrote about that now I wonder why more assholes haven't read the stuff, it seems like they'd like it.
Very similar features, Catnip is Claude Code specific and does everything in a Docker container so you can more safely run in YOLO mode and the Git worktrees don't make a mess on your host filesystem or checkout. Also is mobile responsive which is cute.
Struggling with the same thing right now. I'm trying to make it work by generating unique ports for each instance so they don't conflict. Not quite 100% successful yet.
Curious to hear more.. why is random port selection not working for your case? The other issue we've seen is machines tend to get overloaded with tons of agents running tests concurrently, hence the SSH remote isolation mode.
I recently started using Catnip (https://github.com/wandb/catnip) for this. Catnip also automatically manages multiple Git worktrees, and has a responsive UI for mobile.
reply