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.
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.
Report
Feels like an actual coworker!! What's the practical ceiling on parallel agents per machine before things degrade? Are you seeing teams run 3-5, or 10+?
@bernhard_hausleitner1 it's usually closer to 3 to 5 locally. After that point many users see their machine slow down due to the ram utilization from the many agents. There's definitely demand for more and I expect the ceiling to be much higher once everything moves to the cloud and as the use of long-running agents increases.
Report
Managing multiple coding agents from one place is the right idea - context switching between Claude Code, Codex, and others is its own overhead. Does it unify the context/memory across agents or mostly just the interface?
@lakshminath_dondeti great question! And no, we natively embed the CLI so in the eyes of Claude Code / Anthropic it is as though you're opening Claude Code in any other Terminal emulator like Ghossty, iTerm, etc..
Report
Can I run multiple Claude Code licenses (accounts) and split tasks between them?
@natalia_iankovych yes, you can! Emdash launches the 'real' Claude CLI in a terminal per task, so each new task inherits whatever account you're logged into globally. To switch, you claude logout / claude login and your next task picks up the new account
@alexanderfarr thank you Alex! And congrats on your launch last week!
There're two ways we support remote so far. For one, you can connect to repositories that live on remote servers via ssh and, for another, with BYOI you can run run provisioning and teardown scripts to create a remote workspace per task on your own infra! BYOI is currently still behind a feature flag, but if that's interesting to you, I can enable it for your account!
@sk_uxpin I see! I think the desktop app gives our users currently the most intuitve and extensible interface to work on their issues / tasks and push / review code changes. We might add an Emdash CLI! What's your current setup? Have you tried Emdash?
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.
Feels like an actual coworker!! What's the practical ceiling on parallel agents per machine before things degrade? Are you seeing teams run 3-5, or 10+?
Emdash
@bernhard_hausleitner1 it's usually closer to 3 to 5 locally. After that point many users see their machine slow down due to the ram utilization from the many agents. There's definitely demand for more and I expect the ceiling to be much higher once everything moves to the cloud and as the use of long-running agents increases.
Managing multiple coding agents from one place is the right idea - context switching between Claude Code, Codex, and others is its own overhead. Does it unify the context/memory across agents or mostly just the interface?
Emdash
@imad_elkhafi mainly the interface! Agents still manage their own context / memory
Emdash
@lakshminath_dondeti great question! And no, we natively embed the CLI so in the eyes of Claude Code / Anthropic it is as though you're opening Claude Code in any other Terminal emulator like Ghossty, iTerm, etc..
Can I run multiple Claude Code licenses (accounts) and split tasks between them?
Emdash
@natalia_iankovych yes, you can! Emdash launches the 'real' Claude CLI in a terminal per task, so each new task inherits whatever account you're logged into globally. To switch, you claude logout / claude login and your next task picks up the new account
Clera
Emdash
@alexanderfarr thank you Alex! And congrats on your launch last week!
There're two ways we support remote so far. For one, you can connect to repositories that live on remote servers via ssh and, for another, with BYOI you can run run provisioning and teardown scripts to create a remote workspace per task on your own infra! BYOI is currently still behind a feature flag, but if that's interesting to you, I can enable it for your account!
Just wondering about why desktop and not CLI?
Emdash
@sk_uxpin it is ! You use the CLI agent inside our (desktop) app ✨
@raban makes sense - I was rather referring to CLI agents being used inside a CLI app :)
Emdash
@sk_uxpin I see! I think the desktop app gives our users currently the most intuitve and extensible interface to work on their issues / tasks and push / review code changes. We might add an Emdash CLI! What's your current setup? Have you tried Emdash?