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.
Emdash is a provider-agnostic desktop app to run agents in parallel and turn issues into PRs.
Some features:
Run multiple agents in parallel with isolated worktrees
Use any of 28+ coding agent providers
Pass issues from Linear, Asana, Featurebase, GitHub, …
Run agents on remote machines via SSH
Review diffs and ship PRs in-app
BYOI: provision per-task workspaces on your own infrastructure
Available on macOS, Windows, and Linux
We're excited to see what you're going to build with Emdash!
Report
@arnestrickmann been running into the electron weight tradeoff myself — solo dev, three or four dev tools open at once, and claude code in plain iterm is by far the lightest thing in the lineup. running four parallel agents on long jobs, what matters is whether emdash sits closer to a stack of terminal tabs or to a heavy editor like WebStorm — that's the gap that decides whether you can keep it open all day.
That’s also why SSH support is such a big deal for us: Emdash doesn’t have to be the machine doing all the heavy lifting. You can keep the desktop app as the control plane, while the agents, repos, installs, and long-running jobs happen on a remote machine. For parallel agents, that changes the equation a lot.
Parallel agents with isolated worktrees is the part that catches my eye. Most multi agent desktop tools today are basically tab managers, you flip between sessions but they share the same checkout. Isolated worktrees actually let agents work on the same repo without stepping on each other.
Question on the merge story. When two agents finish parallel tasks that touch overlapping files, what happens? Does Emdash surface the conflict before opening PRs, auto rebase one, or just ship both PRs and let me sort it out on GitHub?
Running a few coding agents in prod today and this is the exact wall I hit, will give Emdash a try this week.
Excited to hear your feedback once you’ve tried Emdash.
If two PRs touch the same files, we surface it via mergeability + CI signals, and you can rebase, resolve conflicts, and merge directly in Emdash (with CI + comments in-app) instead of bouncing to GitHub. (closing the complete development flow)
Report
@arnestrickmann Closing the development flow in app is the right call, the GitHub round trip is where most multi agent setups lose their flow state.
Will give it a real run this week and report back. Good luck with the rest of launch day 🤝
Been using Emdash for the past week and its great. I used to hate working with git worktrees because it made my workflow more complex than it had to be but with Emdash this actually wasn't a problem at all. Im curious though is a ui similar to t3code planned? Would love that a lot!
@dominikkoch that's amazing! And exactly what we initially built Emdash for, to make the wrangling with worktrees and terminal windows a little bit less annoying.
And yes, we'll ship a chatUI similar to T3code soon! We started out with CLIs first because this allows us to ship fastest and offer the full functionality of the CLIs without having to play continuous catchup as they expand their feature set with features such as /btw in claude code.
@fberrez1 thanks you!! We’re building on Electron.
We chose it because Emdash needs a pretty deep desktop runtime: terminals, file watching, Git/worktrees, local DB, provider CLIs, SSH, diffs, etc. Electron gives us the most mature path for that across macOS, Windows, and Linux.
On heaviness: totally fair concern. We’ve spent a lot of time keeping the app responsive and avoiding unnecessary background work. The agents themselves usually dominate CPU/RAM, not the shell UI. That said, we’re actively optimizing startup, task switching etcc!
Let me know how you find it performs, if you end up giving it a shot 🚀🚀🚀
Report
@raban alright, thanks for the explanation. seems a fair choice you made
Congrats on the launch! I really like the multiple agent split view! Is there an option for managing context for each agent, similar to Pi's /tree command?
Very cool. I love this idea. Can it also have automations and crons? This will help teams run the crons locally that are mostly done by individual devs/PMs
@raban This is literally that one feature which will make me switch from Cursor. I always wanted cron/schedules/automations to run locally for some stuff. For stuff where webhooks are involved it might become a little involved, but still could be given for a paid plan (or some plugin).
Also, I hope it works with devcontainers & remote ssh development support.
@pranavprakash yes! It'll work locally initially and then with remote environments. I'll ping you once available 🚀
Report
Running agents in parallel is where things get messy. The unified diff review is the key feature here. Most setups still make you jump between terminals to track what each did. Does Emdash handle merge conflicts when two agents touch the same file, or do they need separate branches?
@dhiraj_patel5 I wouldn't say that the unified diff review is the key feature, but it's definitely nice to have. Key is having multiple agents in parallel across different providers. We don't handle merge conflicts automatically if they come up e.g. because your branch is behind origin. You could typically point your agent at resolving them :)
I saw AntiGravity recently went in the same direction as of yesterday. They basically removed the IDE part and doubled down on Agent control tower. How is emdash different from AntiGravity?
We think agent-focused views are the next UI primitive for managing fleets of agents. And as you mentioned, Antigravity is moving in a similar direction.
One core difference is that Emdash is deliberately provider-agnostic. You’re not locked into one agent, model, or harness - you can run Codex, Claude Code, Grok, Devin, and the rest of the 28+ coding agents we support.
On top of that, Emdash is built around bringing agents into your existing workflow: issues from GitHub/Linear/Asana/etc., isolated worktrees, SSH/remote machines, diff review, and PR shipping in one place.
Emdash
Hey Product Hunt! 👋
We’re super happy to show you Emdash today.
One app, every coding agent.
Emdash is a provider-agnostic desktop app to run agents in parallel and turn issues into PRs.
Some features:
Run multiple agents in parallel with isolated worktrees
Use any of 28+ coding agent providers
Pass issues from Linear, Asana, Featurebase, GitHub, …
Run agents on remote machines via SSH
Review diffs and ship PRs in-app
BYOI: provision per-task workspaces on your own infrastructure
Available on macOS, Windows, and Linux
We're excited to see what you're going to build with Emdash!
@arnestrickmann been running into the electron weight tradeoff myself — solo dev, three or four dev tools open at once, and claude code in plain iterm is by far the lightest thing in the lineup. running four parallel agents on long jobs, what matters is whether emdash sits closer to a stack of terminal tabs or to a heavy editor like WebStorm — that's the gap that decides whether you can keep it open all day.
Emdash
@webappski Totally fair point.
That’s also why SSH support is such a big deal for us: Emdash doesn’t have to be the machine doing all the heavy lifting. You can keep the desktop app as the control plane, while the agents, repos, installs, and long-running jobs happen on a remote machine. For parallel agents, that changes the equation a lot.
@arnestrickmann Hi Arne, big congrats on the launch 🎉
Parallel agents with isolated worktrees is the part that catches my eye. Most multi agent desktop tools today are basically tab managers, you flip between sessions but they share the same checkout. Isolated worktrees actually let agents work on the same repo without stepping on each other.
Question on the merge story. When two agents finish parallel tasks that touch overlapping files, what happens? Does Emdash surface the conflict before opening PRs, auto rebase one, or just ship both PRs and let me sort it out on GitHub?
Running a few coding agents in prod today and this is the exact wall I hit, will give Emdash a try this week.
Emdash
@artem_fedorovich Thank you!
Excited to hear your feedback once you’ve tried Emdash.
If two PRs touch the same files, we surface it via mergeability + CI signals, and you can rebase, resolve conflicts, and merge directly in Emdash (with CI + comments in-app) instead of bouncing to GitHub. (closing the complete development flow)
@arnestrickmann Closing the development flow in app is the right call, the GitHub round trip is where most multi agent setups lose their flow state.
Will give it a real run this week and report back. Good luck with the rest of launch day 🤝
Emdash
@artem_fedorovich Thank you!
Looking forward to hearing your thoughts!
Notra
Been using Emdash for the past week and its great. I used to hate working with git worktrees because it made my workflow more complex than it had to be but with Emdash this actually wasn't a problem at all. Im curious though is a ui similar to t3code planned? Would love that a lot!
Emdash
@dominikkoch that's amazing! And exactly what we initially built Emdash for, to make the wrangling with worktrees and terminal windows a little bit less annoying.
And yes, we'll ship a chatUI similar to T3code soon! We started out with CLIs first because this allows us to ship fastest and offer the full functionality of the CLIs without having to play continuous catchup as they expand their feature set with features such as /btw in claude code.
Notra
@raban awesome, can't wait!
Very cool project
i’m curious what you’re building on: Tauri, Electron, or something else?
I'm looking for a software that is not too heavy to run. Do you have any insights?
Emdash
@fberrez1 thanks you!! We’re building on Electron.
We chose it because Emdash needs a pretty deep desktop runtime: terminals, file watching, Git/worktrees, local DB, provider CLIs, SSH, diffs, etc. Electron gives us the most mature path for that across macOS, Windows, and Linux.
On heaviness: totally fair concern. We’ve spent a lot of time keeping the app responsive and avoiding unnecessary background work. The agents themselves usually dominate CPU/RAM, not the shell UI. That said, we’re actively optimizing startup, task switching etcc!
Let me know how you find it performs, if you end up giving it a shot 🚀🚀🚀
@raban alright, thanks for the explanation. seems a fair choice you made
good luck!
Sitefire
Congrats on the launch! I really like the multiple agent split view!
Is there an option for managing context for each agent, similar to Pi's /tree command?
Emdash
@jochenmadler somewhat! We don't have a separate context management layer, but you can use Pi with it's /tree command right inside of Emdash
Fere AI
Emdash
@pranavprakash yes! We have an open 'automations' PR! Coming very soon
Fere AI
@raban This is literally that one feature which will make me switch from Cursor. I always wanted cron/schedules/automations to run locally for some stuff. For stuff where webhooks are involved it might become a little involved, but still could be given for a paid plan (or some plugin).
Also, I hope it works with devcontainers & remote ssh development support.
Emdash
@pranavprakash yes! It'll work locally initially and then with remote environments. I'll ping you once available 🚀
Running agents in parallel is where things get messy. The unified diff review is the key feature here. Most setups still make you jump between terminals to track what each did. Does Emdash handle merge conflicts when two agents touch the same file, or do they need separate branches?
Emdash
@dhiraj_patel5 I wouldn't say that the unified diff review is the key feature, but it's definitely nice to have. Key is having multiple agents in parallel across different providers. We don't handle merge conflicts automatically if they come up e.g. because your branch is behind origin. You could typically point your agent at resolving them :)
DiffSense
I saw AntiGravity recently went in the same direction as of yesterday. They basically removed the IDE part and doubled down on Agent control tower. How is emdash different from AntiGravity?
Emdash
@conduit_design Hi!
We think agent-focused views are the next UI primitive for managing fleets of agents. And as you mentioned, Antigravity is moving in a similar direction.
One core difference is that Emdash is deliberately provider-agnostic. You’re not locked into one agent, model, or harness - you can run Codex, Claude Code, Grok, Devin, and the rest of the 28+ coding agents we support.
On top of that, Emdash is built around bringing agents into your existing workflow: issues from GitHub/Linear/Asana/etc., isolated worktrees, SSH/remote machines, diff review, and PR shipping in one place.