Launching today
TUICommander
AI-native IDE for multi-agent development
11 followers
AI-native IDE for multi-agent development
11 followers
Run parallel AI coding agents on isolated branches with full observability. Diffs, PRs, CI status, usage dashboards, one workspace, zero context loss. Auto-detects 11 agents (Claude Code, Codex, Aider, Gemini CLI, Amp, and more) with rate limit countdowns and question detection. Git worktree isolation per branch. MCP Proxy Hub. CI Auto-Heal. Built-in AI Chat (Ollama, Anthropic, OpenAI). Mobile PWA companion. Rust + SolidJS. ~80MB RAM. macOS, Linux, Windows. Apache 2.0.
I started using TUICommander weeks ago and it has been a game changer.
Tired of losing track of what I was working on across so many tabs in the terminal, drowning in the branch and project mess, I started using other tools like suppacode to help me improve my performance. Even if it helped, they were missing something.
TUICommander hit the spot. I can have everything I need in a single tool. Github? Check. VS Code? Check. Terminals? Check. Proper management of projects, branches and worktrees? Check.
What made it shine even more, were the extra tools it offered me. Markdown lists so I can have quick access to my plans or .md files. The ideas feature allowing me to queue thousands of thoughts while AI is working on my latest prompt.
When you start using it, it's great. When you start using every tool it offers you, it's amazing.
@achelonmm thank you! Really appreciate you taking the time to write this. The part about discovering features over time is exactly how I hoped people would use it. The terminal management gets you started, but the real value comes from the tools around it: markdown viewer, ideas queue, worktree management and upcoming AI companion for AIs.
I’ve been using TUICommander with both Claude Code and Codex, and honestly it solves a very real problem: keeping multiple AI coding sessions under control without losing context.
The biggest value for me is being able to run parallel sessions, switch between branches/worktrees, and still have a clear view of what each agent is doing. Once you start using Claude Code and Codex together, a normal terminal setup quickly becomes messy. TUICommander makes that workflow feel organized instead of chaotic.
Great tool, especially if you are seriously using AI agents for development rather than just trying them casually.
@roberto_serafin Fair point 😄 there are definitely things that don’t work yet and need fixing.
There’s a lot going on, and without feedback, some edge cases inevitably slip through.
The core focus, though, is exactly what you described: making multi-agent workflows structured instead of chaotic.
The tool is intentionally non-opinionated, so you can build your own setup rather than adapting to a predefined one.
It can feel a bit complex at first, but once you dial in your workflow, it’s hard to go back.
"Amazing launch, @stefanostraus ! Having seen the evolution of TUICommander at Lansweeper, I can vouch for the boost in productivity it provides. As a Quality Engineer, I love the Git worktree isolation—it’s essential for maintaining clean testing environments while running multiple AI agents. The attention to detail is top-notch. Upvoted! 🚀"
Thank you, really appreciate @mendezdaniela
This is the thing I didn't know I was waiting for!
Running more than one coding agent in parallel today means juggling terminals, forgetting which branch is which, and missing a Y/n prompt that blocks progress for an hour.
Solving that with per-branch worktrees + a unified view of what every agent is doing is exactly the right abstraction. Upvoted and congrats on shipping 👏
@federico_nicolelli thank you for the support. Parallel execution is the key to agentic coding. It's not about running agents but about orchestrating the environment without jumping from one tool to another.