Hey HN! We’re Arne and Raban, the founders of Emdash (https://github.com/generalaction/emdash).Emdash is an open-source and provider-agnostic desktop app that lets you run multiple coding agents in parallel, each isolated in its own git worktree, either locally or over SSH on a remote machine. We call it an Agentic Development Environment (ADE).
You can see a 1 minute demo here: https://youtu.be/X31nK-zlzKo
We are building Emdash for ourselves. While working on a cap-table management application (think Stripe Atlas + Pulley), we found our development workflow to be messy: lots of terminals, lots of branches, and too much time spent waiting on Codex.
Emdash puts the terminal at the center and makes it easy to run multiple agents at once. Each agent runs as a task in its own git worktree. You can start one or a few agents on the same problem, test, and review.
Emdash works over SSH so you can run agents where your code lives and keep the parallel workflow. You can assign tickets to agents, edit files manually, and review changes.
We also spent time making task startup fast. Each task can be created in a worktree, and creating worktrees on demand was taking 5s+ in some cases. We now keep a small reserve of worktrees in the background and let a new task claim one instantly. That brought task start time down to ~500–1000ms depending on the provider. We also spawn the shell directly and avoid loading the shell environments on startup.
We believe using the providers’ native CLIs is the right approach. It gives you the full capabilities of each agent, always. If a provider starts supporting plan mode, we don't have to add that first.
We support 21 coding agent CLIs today, including Claude Code, Codex, Gemini, Droid, Amp, Codebuff, and more. We auto-detect what you have installed and we’re provider-agnostic by design. If there’s a provider you want that we don’t support yet, we can add it. We believe that in the future, some agents will be better suited for task X and others for task Y. Codex, Claude Code, and Gemini all have fans. We want to be agnostic and enable individuals and teams to freely switch between them.
Beyond orchestration, we try to pull most of the development loop into Emdash. You can review diffs, commit, open PRs, see CI/CD checks, and merge directly from Emdash once checks pass. When starting a task, you can pass issues from Linear, GitHub, and Jira to an agent. We also support convenience variables and lifecycle scripts so it’s easy to allocate ports and test changes.
Emdash is fully open-source and MIT-licensed.
Download for macOS, Linux or Windows (as of yesterday !), or install via Homebrew: brew install --cask emdash.
We’d love your feedback. How does your coding agent development setup look like, especially when working with multiple agents? We would want to learn more about it. Check out our repository here: https://github.com/generalaction/emdash
We’ll be around in the comments — thanks!
▲Here's my question:
if agents continue to get better with RL, what is future proof about this environment or UI?
I think we all know that managing 5-10 agents ... is not pretty. Are we really landing good PRs with 100% cognitive focus from 5-10 agents? Chances are, I'm making mistakes (and I assume other humans are too)? Why not 1 agent managing 5-10 agents for you? And so on?
Most of the development loop is in bash ... so as long as agents get better at using bash (amongst other things), what happens to this in 6 months?
I don't think this is operating at a higher-level of abstraction if agents themselves can coordinate agents across worktrees, etc.
nemooperans23 minutes ago
[-] Having built and run agentic systems in production — the "why not agents managing agents" question has a practical answer: the orchestration layer is where the most expensive mistakes happen. Trust boundaries, escalation decisions, when an agent should act vs ask — that's engineering judgment, not boilerplate.
What's future-proof isn't the UI chrome, it's maintaining human visibility into the decision layer. The agents will get better at everything below that line. The line itself is the thing worth building tools around.
Interesting thoughts - thank you! And directionally agree - given that agents are becoming ever better, they'll take more and more of the orchestration on themselves. Still, we believe that developers need an interface to interact with these agents; see their status and review / test their work. Emdash is our approach for building this interface of the future - the ADE :)
reply▲> Still, we believe that developers need an interface to interact with these agents;
CLIs like claude code equally improve over time. tmux helps running remote sessions like there were local.
Why should we invest long time into your „ADE“, really?
> see their status and review / test their work
Won’t that be addressed eventually by the CLIs themselves?
Maybe you’re betting on being purchased by one of the agentic coding providers given your tool has long term value on its own?
So, what's your business model ? Is this an YC product, or a tool you developed while working on a YC product ?
reply▲onecommit20 minutes ago
[-] We're figuring our business model out. There're two avenues that we principally think about (1) bundled coding agent subscription and (2)enterprise version with auth, team management, sharing of agent interactions. Admittedly, it's early and this can change. What won't change is that this UI layer for running multiple coding agents is and will be open-source. Emdash itself is funded by YC. Initially developed as a tool while working on another product, but we weren't funded then.
reply▲(2) sounds like a great idea if you can ensure private company data never reaches your servers, with features like remote controlling agents from a central place
reply▲Been driving my agents (CC, currently testing Pi) for a couple of weeks via Emdash. Finally, got a productive worktree setup working. There were still rough edges when I started, but the team has shipping fast [0] and is vaporizing concerns on the fly. Building on top of the native CLI seems to be the right strategy as well.
[0] https://github.com/generalaction/emdash/releases/
the worktree pre-warming detail is interesting -- keeping a reserve pool and letting new tasks claim one instantly is the same pattern as connection pool pre-warming in databases. the underlying bottleneck is probably git having to traverse pack files and update the index when you run 'git worktree add'. one thing worth trying if you haven't: sparse checkout on the worktrees can cut that initialization time further, especially in large monorepos where most files are irrelevant to a given agent task.
reply▲onecommit56 minutes ago
[-] interesting! hadn't looked into sparse checkout before, but will do now. Initial thoughts are that sparse might be risky if we lose some arbitrary files that might be relevant context for the coding agents. Will look into this!
reply▲bketelsen35 minutes ago
[-] this looks great, but can't test, the .deb package is broken with an issue about NODE_MODULE_VERSION mismatches. There seems to be a PR waiting for approval. Will keep an eye on it.
reply▲FiloVenturini2 hours ago
[-] Have you considered adding any kind of agent coordination layer, e.g. letting one “orchestrator” agent spawn and direct sub-agents on specific subtasks, rather than having the developer manually assign each task? Or is the explicit human-in-the-loop assignment a deliberate design choice to keep control and avoid runaway costs?
reply▲We've considered it! The way we're seeing it, this is something that the CLIs themselves are getting good at natively, such as Claude Code. We generally consider ourselves to be at a higher abstraction / task level, where the individual CLIs are responsible themselves for breaking down and distributing a larger task across subagents.
reply▲das-bikash-dev2 hours ago
[-] How does Emdash handle state management when running multiple agents on the same codebase? Particularly interested in how you prevent conflicts when agents are making concurrent modifications to dependencies or config files. Also, does it support custom agent wrappers, or do you require the native CLI?
reply▲Thanks for your questions! You can separate the agents in Emdash by running them on separate git worktrees so they can do concurrent modifications without interfering. We don't support custom agent wrappers currently, interesting. Have you written your own? What is your use case for them over native CLIs?
reply▲> Each agent runs as a task in its own git worktree
If you're talking about shared services, that's another matter.
Let's go! Love that this is a solid OSS alternative to what's already out there!
reply▲Pretty sick. How do you compare yourself with Conductor?
reply▲Conductor is definitely in the same space. Main points of differentiation that I am aware of are that we allow you to connect to remote servers via SSH, natively embed many more coding agents (21) with their full functionality, and are open-source.
reply▲i'll have to give it a shot, the market needs an open source cursor right now
reply▲great! send all feedback our way :folded_hands:
reply▲Looks cool! Thank you for sharing.
reply▲Is this another VSCode fork? I can’t tell from the readme.
reply▲Not in its purest sense! We're using the monaco editor for file editor and diffs, but other than that no VScode included. The file editor is really a secondary view inside of Emdash. The focus is on the chat with the coding agent. We'll make this more clear in the readme. Thanks for the feedback!
reply