Emdash is an open-source desktop app for running multiple coding agents in parallel; one place to monitor sessions, review diffs, and turn issues into PRs.
Free
Launch Team
Floot MCPBuild and ship web and mobile apps inside Claude or ChatGPT
Promoted
@marc_klingen thank you Marc! Langfuse has been a big inspiration to us, especially on open-source and 'docs are product'. Though admittedly our docs need more love. 😀
I think the main difference is flexibility.
You can use the provider you want, with the issue tracker you use, on the OS you’re on. Agents can run locally or on your own machines over SSH.
Another critical differentiation (particularly with last weeks policy updates from Anthropic): We run the actual CLIs in our terminal emulator. So you get the real Claude Code, Codex, Gemini, OpenCode, etc. experience, with the latest models. ✨
Emdash is best for engineers and teams who already code nearly exclusively with coding agents nearly exclusively, and want a cleaner way to run them across providers and machines with a deep git integration and easy way to review changes.
Nice. That can make my life much easier. What features that come up in the next few weeks are you most excited about? Can you share a bit more about the roadmap?
@mikemahlkow wow, thank you! Big fan of Fastgen here!
We're really excited about remote development in general. With coding agents more than ever it makes sense to move development to the cloud for (1) session persistence, (2) scale (not eating all your RAM while running 10+ agents), and (3) accessibility across devices. That way you can access session from desktop, web, and mobile. We'll launch lots in that direction next :)
Congrats on the launch! Parallel agent sessions with a unified diff view is exactly where the workflow needed to go. The PR-from-issue flow is particularly smart for async teams. What's the mental model for context isolation between sessions?
@tonyspiro thanks Tony! Each task has its own git worktree so the code changes in sessions/tasks are fully isolated. Ports, dbs, and node_modules e.g. are still shared across tasks on a given device. We make that easy to handle with convenience variables to give you different ports per task e.g. and we'll launch more complete isolation soon! :)
The possibility to use the native CLIs of Codex and Claude Code is kinda the game changer here. Especially, with all that Claude token billing debacle that's going on
@samuel_stroschein couldn't have said it better!
Very big fan of Emdash. It's been incredible seeing how fast the team is shipping new features and expanding it. I love how I can run my agents in parallel and also across different models. Finally, I don't have to migrate back and forth between Claude Code and Codex every month.
@dan_meier1 thank you Dan! Your feedback has been invaluable!
I have been using Emdash for three months now and I really like it! Compared to other agentic development environments, Emdash is the best fit for my workflow. It makes me much faster because it's so easy to work on multiple things at once in different worktrees or run different agent sessions in parallel in the same worktree 👏
@soenkep Thank you for your continuous feedback on how we can make the product better for you!
Keep it coming:)
I've been using emdash for the past week and have loved it.
Before this, I’d looked into using git worktrees to run more agents in parallel, but the extra workflow overhead made it hard to justify adopting them day to day.
Emdash abstracts all of that away. It makes spinning up parallel agents feel simple and natural.
You can also feel the craft in the product. Little touches like creating an agent from a GitHub issue, the animations, and the sounds make the app genuinely enjoyable to use.
If you want to run multiple agents in parallel and let them rip, I highly recommend trying Emdash.
@enrique_goudet Thank you, really appreciate that!
That worktree overhead was exactly one of the things we wanted to make disappear. Please keep the feedback coming - it’s super valuable.