Run multiple Claude Code agents in parallel, each in its own git worktree, each with its own session and terminal. Claudette also supprots remote sessions run on another machine over an encrypted WebSocket connection. Full editor support means you can stay in one app for chat, diffs, terminal, and editor.
So why did we build Claudette? We liked Conductor and similar tools but didn't love that they weren't open source or required a login to use. So we set out to fill that gap, and address a few other things we wanted along the way.
We're continuing to add features with recent additions being Windows support, OpenPeon sound pack integration (300+ packs to pick from, Alan Rickman being my favorite), Monaco integrate for full editor support, and more.
We've got some really exciting features baking right now that should be dropping soon.
Feedback and thoughts welcome!
This project is open source and contributions are welcome, but also any and all feedback. I think we've made something really powerful and really fun, excited to share it.
Also, I highly recommend the Alan Rickman soundpack.
And a couple of things happening with that are similar to what Claudette is doing.
Having each agent have their own version of the project is the best basic way to set it up. But the slowdown isn't how well the files are kept separate from each other after a short time, it's that each of these versions of the task slowly changes in how they understand things, and this difference doesn't show up until you look at three totally separate answers. I was constantly creating a single place to see how much of Claude's allowance each one was using, what stage of the process each was at, and what each had most recently done with a tool, and I did this by hand with tmux and jq before deciding it wasn't going to be a good solution.
congrats on shipping.