I'm so married to my existing tmux workflows and layout that I'm not sure whether I'd ever feel open to trying out something like this. At the same time, orchestrating multiple agents with native tmux and git worktree does feel cumbersome.

I'm also trying to build something similar for agent orchestration where one terminal is controlling multiple terminals. I tried using tmux but it's very good at sending the initial text to the tmux sessions, but I've not been able to get an agent to have a proper back and forth controlling multiple tmux sessions. I know we can use send-keys, but reading the session or knowing when that session is complete is kind of up in the air. And then if the main orchestrator terminal has checked all the sessions to see if they're actually working and doing things, the main session kind of stop so I've kind of been thinking about a cron that periodically checks in and nudges it to check the sessions again. Are they still working? Do they need more guidance? Essentially having one terminal control others, but having that back and forth with the terminals has been pretty challenging to achieve. Have you gotten anywhere with this?

If this supported Gemini and Codex I would find it useful. I never run more than one Claude, it's always a mix.

Looks like a great implementation. I want to question the basic user story, which seems to be: "I am a software developer who wants to improve productivity by running multiple simultaneous agents that are roughly isomorphic to a human software developer team."

I am burning a lot of tokens every day at work and on personal projects. It's helpful. I generally work in tmux with github copilot in one pane, and a few other terminal panes showing tests and current diff.

I find it really important to avoid the temptation to multi-task by running multiple agents. For quite varied tasks, productivity gains from multi-tasking have proven to be illusory. Why would it be different with writing software?

https://en.wikipedia.org/wiki/Human_multitasking

I went the web route and run tmux inside docker sandboxes with a ghostty-based terminal: https://github.com/rcarmo/webterm

https://github.com/ehrlich-b/wingthing Here’s my take on this idea, also FOSS. Does tmux style sessions so you can come and go. It also exposes a web terminal so you can get remote access - but you can also run fully locally for less latency.

I've been looking for something like this - in fact, I've found several but they've all been MacOS only until now. So great job on making yours cross platform.

Interesting, but I wonder if this shifts too much complexity onto the user.

tmux is powerful, but not exactly approachable, and "multi-agent orchestration" on top of it feels like something that could get hard to reason about quickly. Curious how you think about UX here.

I built a very similar one that I use every day, smux: https://github.com/gergomiklos/smux. Took only 1 hour with claude.

Terminal-first makes a lot of sense for anything that runs on remote servers. I've been on helix+tmux for about a year and the main friction is onboarding teammates who are VSCode-native. Nice to see projects pushing in this direction. Does it handle multi-pane debugging or is that still a manual tmux split?

Congrats on getting this out. What was the most surprising part of the build?

Can somebody develop a mobile app that natively supports tmux

interesting results but the eval methodology seems a bit optimistic

I like a good CLI, I like a good TUI, but why are we eschewing high-DPI graphical displays, icons, true-color, images, and everything else in favour of a 1980s terminal? Is it just to be retro, or do you guys really think you're seeing some advantage restricting yourself like this? Do you all REALLY hate moving your hand over to your mouse?

So basically tmuxinator?

Thank you for sharing your work. Really cool.

From my perspective, this is cool, but since tmux is kind of permanent, you open your layout, set 1,2,3 screens for agents, you might add gemini and opencode. then open vite for server and one for shell for example. Then you can just close it and reopen whenever you want to work on it.

And that is it. If I am missing something, processes taking memory or such, I have a machine with memory (I know, flexing how expensive things are), please explain.

undefined

[dead]

[flagged]

[dead]

[dead]

[dead]

[flagged]

[flagged]

[flagged]