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.
thijsverreck 2 hours ago [-]
if you want you can file an issue with your current workflow? happy to see if we can do a PR to support this natively in tmux-ide
selixe_ 1 hours ago [-]
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.
thijsverreck 55 minutes ago [-]
Good points and indeed thinking about this quite a bit. Currently leaning towards a CLI first approach so that Claude/Cursor/[insert coding agent] can configure and control the ide. Feels a bit meta, but also makes it extremely user-friendly.
j45 55 minutes ago [-]
Tmux is pretty easy to pick up and build muscle memory by learning a few keyboard shortcuts from a basic youtube video and it's handy when you don't want to switch screens between multiple terminals just for one thing.
The ability to split and divide the screen pretty simply with a few keys is handy for anyone who spends enough time in a shell - the abilty to save that layout for the shell items you're using to load up easily again the next time is valuable too.
Multi agent orchestration likely just means keeping track of a few different windows all on one screen.
operatingthetan 1 hours ago [-]
If this supported Gemini and Codex I would find it useful. I never run more than one Claude, it's always a mix.
thijsverreck 57 minutes ago [-]
Both are supported! You can customize the startup command in ide.yml. I will update the docs to highlight that :)
theturtletalks 3 hours ago [-]
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?
SparkyMcUnicorn 2 hours ago [-]
It sounds like maybe you haven't seen agent teams mode, which this project is using.
Oh will definitely look into this! I ditched CC for Pi a few months ago so maybe there’s an equivalent feature.
thijsverreck 2 hours ago [-]
yup core to this project!
bwestergard 3 hours ago [-]
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?
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?
I love cmux! ironically you can use tmux-ide within cmux. The idea is to make it an agent development environment that's great when ran on a remote machine :).
Congrats on getting this out. What was the most surprising part of the build?
thijsverreck 2 hours ago [-]
most surprising was that something this lightweight made such a big impact on my productivity. its really nice to have persistent Claude teams on my remote machines that I can always access no matter what.
jamesvzb 29 minutes ago [-]
open source alternatives are catching up fast. give it 6 months
mlboss 2 hours ago [-]
Can somebody develop a mobile app that natively supports tmux
jrop 2 hours ago [-]
I assume that you've tried Termux and somehow that doesn't meet your needs? (Also, you didn't specify whether you are on Android/iOS)
thijsverreck 2 hours ago [-]
both ish and termux are great options on mobile/iPad!
deadbabe 2 hours ago [-]
For all the hype of AI agents, you never see people taking on real challenging projects like this. Just low hanging fruit.
AtxWrk70 52 minutes ago [-]
the token costs are real. we switched to smaller models for 80% of tasks and barely noticed
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.
The ability to split and divide the screen pretty simply with a few keys is handy for anyone who spends enough time in a shell - the abilty to save that layout for the shell items you're using to load up easily again the next time is valuable too.
Multi agent orchestration likely just means keeping track of a few different windows all on one screen.
https://code.claude.com/docs/en/agent-teams
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