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.
No reviews yetBe the first to leave a review for Emdash
getviktor.comAn AI coworker that actually does the work
Promoted
Congrats on the launch. The worktree + PR handoff is the part I’d try first. One thing I’m curious about: when several agents touch adjacent files, does Emdash help compare runs and trace which prompt or session introduced a change, or is the review flow mainly diff-first today?
Report
It literally feels like a real developer. Curious how you’re handling context synchronization between agents working on related parts of the same codebase.
Report
Running multiple coding agents in parallel is something I've wanted for a while — usually you have to babysit each one separately. The isolated worktrees approach makes sense, keeps agents from stepping on each other's work. Would love to know how the PR review flow works when 3-4 agents finish at different times — does it queue them or let you review as they come in?
Report
When multiple agents are working on related parts of the same codebase in parallel, how does Emdash handle potential conflicts — does it surface them before you hit merge, or is that left to the user to catch?
Report
the parallel agents angle is the part worth exploring. running multiple coding agents simultaneously sounds powerful until you hit merge conflicts from two agents touching the same files. curious how Emdash handles that, is there any coordination layer between sessions or is it essentially isolated workspaces that you reconcile manually through the diff review
Report
Interesting seeing the shift from IDE-centric AI tooling to agent orchestration layers. Curious how you think Emdash evolves once agents start depending on outputs from each other, not just running in parallel. Does coordination between agents become part of the product long term?
Report
Curious whether Emdash handles context about non-code file types in a repo — specifically design assets like WOFF2 fonts, compiled CSS, and SVG icon sets. Design system repos mix code and compiled assets heavily, and most agent tools treat everything as code. Does Emdash pass that file-type context to the agent or leave it to the agent to infer?
Congrats on the launch. The worktree + PR handoff is the part I’d try first. One thing I’m curious about: when several agents touch adjacent files, does Emdash help compare runs and trace which prompt or session introduced a change, or is the review flow mainly diff-first today?
It literally feels like a real developer. Curious how you’re handling context synchronization between agents working on related parts of the same codebase.
Running multiple coding agents in parallel is something I've wanted for a while — usually you have to babysit each one separately. The isolated worktrees approach makes sense, keeps agents from stepping on each other's work. Would love to know how the PR review flow works when 3-4 agents finish at different times — does it queue them or let you review as they come in?
When multiple agents are working on related parts of the same codebase in parallel, how does Emdash handle potential conflicts — does it surface them before you hit merge, or is that left to the user to catch?
the parallel agents angle is the part worth exploring. running multiple coding agents simultaneously sounds powerful until you hit merge conflicts from two agents touching the same files. curious how Emdash handles that, is there any coordination layer between sessions or is it essentially isolated workspaces that you reconcile manually through the diff review
Interesting seeing the shift from IDE-centric AI tooling to agent orchestration layers. Curious how you think Emdash evolves once agents start depending on outputs from each other, not just running in parallel. Does coordination between agents become part of the product long term?
Curious whether Emdash handles context about non-code file types in a repo — specifically design assets like WOFF2 fonts, compiled CSS, and SVG icon sets. Design system repos mix code and compiled assets heavily, and most agent tools treat everything as code. Does Emdash pass that file-type context to the agent or leave it to the agent to infer?