Launch HN: Superset (YC P26) – IDE for the agents era (github.com)

108 points by avipeltz ↗ HN
Hey HN, we’re Avi, Kiet, and Satya. We’re building Superset (https://github.com/superset-sh/superset), an open-source agentic IDE for running coding agents like Claude Code, Codex, OpenCode etc in parallel.

Demo: https://www.youtube.com/watch?v=YWDHn7gUwfg

Try it: https://superset.sh/

We’re three engineers who’ve built and maintained large codebases, and we kept wanting to work on more than one thing at a time. Once CLI coding agents got good enough we found ourselves running several of them in parallel: triaging Github issues, adding a few ui features, reviewing PRs, researching a refactor, etc.

The funny part was that we and a lot of our friends had all hacked together similar scripts around git worktrees. Worktrees are a nice primitive for this because each agent can get an isolated copy of the repo, but the workflows around them can feel pretty messy, setting up/tearing down environments and managing dev servers.

We first posted here a few months ago when Superset was mostly an open-source terminal for managing git worktrees (https://news.ycombinator.com/item?id=46368739). Since then, it has changed a lot based on feedback from people using it on real codebases, plus contributions from our open-source community. The product has grown into something closer to an IDE for managing agent work across many worktrees, repos, and machines.

The biggest thing we learned is that the hard part is not just “run more agents.” It is managing all the state around them: worktrees, ports, terminal sessions, environment setup, diffs, tasks, and PRs. Once you have five or ten agents running, the bottleneck often becomes remembering what each one is doing and actual human review. We added task / issue tracking so work can move from issue → agent → diff → PR → review without losing the context all in Superset. But there's a lot more work to improve this experience over time.

We also launched Remote Workspaces, currently in beta. The idea is that you can run coding agents on remote machines instead of using all the memory and CPU on your laptop, while still managing the work from the Superset desktop app.To support Remote workspaces, we isolated the core functionality of our Electron app into a headless Hono server such that it can be deployed into any workspaces and talk to any client (such as our desktop app, mobile, web, etc) and still provide the same interface that our desktop app has.

A lot of our next work is around making agent work easier to manage when you are not sitting at your main dev machine. We’re building more functionality into the Superset CLI, improving remote workspace flows, and working on Superset Mobile (coming soon) so you can check on agents, review progress, and steer work from your phone.

We’d love more feedback on Superset, especially if you are daily driving coding agents!

64 comments

[ 5.2 ms ] story [ 53.7 ms ] thread
How does this compare to Cursor?

What happens if Cursor makes the exact same features as your product?

I agree with the hard part being managing state, especially environments and ports. I've never used lsof so much in my life.

Question on Remote Workspace: Can the remote machine port forward so I can use a browser to see / test current state of the app on the remote machine?

I'd love a comparison to what's already out there. Don't vscode, antigravity, cursor etc all have agents too?
Nice. In the right track. I made something similar, but focused on local agents, but we both have issue tracking for managing multiple project and agents in parallel. It works, I think people will be surprised when they start using systems like this.

It is very different from current editors and the direction they are going in. In a way, it undermines the direction they are going. Current editors aim to make engineers 10x or 100x. These editors aim at a different target than the engineers. I will leave it to the imagination on who.

Binding the shell <-> local git clone automatically feels like the future. Great work.
Confusing name. Superset is already an established analytics tool.
zed , orca , /.+mux.*/ , ...

they all look incredibly / increasingly the same?

At first glance, it looks similar to Conductor (https://www.conductor.build/). It seems like a lot of these tools are converging on the same general ideas.

Could you share a comparison with the other tools out there?

For me the greatest difference is that superset is terminal-centric while conductor is chat-centric.

GUIs slow you down, in my opinion. But having the nice visual diff is something we can't really do well in TUIs, so very welcome.

So, superset, for me (been using for quite some time now) is basically to organize my agent and terminal sessions per task and project.

I can switch context much easier and can also resume working on something days later, with all my tabs nicely available and separated.

This was consuming me before, a dozen or more tabs and windows in my computer that I don't really remember to which task each belongs to.

I've been using this for the past few months, and I love it! It's built exactly around my workflow with many worktrees in various repos open at the same time, sometimes with different agents working side-by-side. Before Superset I just used terminal tabs but simply couldn't manage more than like 20 terminal tabs without losing track, so i coudn't scale further. Now i'm running probably 40-50 agent sessions over several repos simultaneously without any issues and losing track! Keep up the good work guys!
No linear integration in free version and taxing it 20$/m is a bit steep.
is it terminal on steroids some kind of? so you can manage mutiple coding agents? how many coding agents you can manage in parallel that it is still comfortable to work and code changes are meaningful
How do you guys plan to sustain the business, given that your product here is open source & already has many competitors doing similar things?
The FAQ says "Superset has a free tier. The source code is available on GitHub under Elastic License 2.0 (ELv2), so you can inspect and self-host it subject to the license terms." - what is self hosting in this context, isn't it a desktop app? Is this why it wants me to sign into something? What exactly am I signing in to?
Personally, IDE for the agent era is just Linux.

Kitty with oh-my-zsh, lazyvim and an agent. The entire thing is an ide. If I need to refactor, query data and interact with the system I just use native tools like rg+fastmod, bash, awk, jq... Either writing myself of asking an agent to do the heavy lifting.

Linux in the agent era is a breeze to operate and reason about, so the whole thing becomes a single development environment that's really light on resources and effective.

I used Superset for quite a while until a month ago. There were some annoying issues, with freezing and terminal not being rendered how it should be. And they did repeated fixes that didn't really solve it. Since I had work to do I moved on.

I installed Zellij on my server where most of work is happening and local machine and this works well for me. There are other issues I have now, but overall flow is fairly natural to what I am doing.

I liked that they did integrate a lot of agent workflow in Superset but my experience was that it would just take too many resources and especially with glitches, it wasn't worth it continuing. I had a period where i enjoyed working in it. It is vibe coded electron app, 2GB! is too much for this kind of app.

I just updated to their new version... it supposedly imported my projects but I can't find anything... so... I guess this is it.

How many "IDEs for the agentic era" do we need?
This uses separate git worktrees. If we have a local dev setup involving multiple docker services, is there a recommended solution for managing those envs? I didn't see.
Is anyone actually using agent swarms for anything real?
for clarification we're less of a agent swarm tool, and more of a launch a bunch of independent agents in isolated environments and have some nice UX to manage them too. I also havent had as much luck with agent swarms or ralph loops, but i'm sure the laps will improve them with time
Why Mac only?

Also - one issue I've seen with other tools doing worktree stuff is they don't deal with merge conflicts automatically. IMO the agents should just automatically resolve conflicts & rebase on their own, is that a thing here?

Surely that's something you just instruct the model to do in your CLAUDE.md / AGENTS.md right? Not really the domain of the IDE.
We technically have a linux build, but dont maintain it as well as mac. We are built on electron so eventually we want to more heavily support linux and windows but we dont currently have anyone on the team that daily drives linux and windows the maintenance overhead is a bit too high. Once we do have someone on the team driving linux/windows we'll have broader publicized support for all platforms.

And on the worktree note, I find when working in a worktree the agent has a much easier time solving merge conflicts and as the number of feature branches scale and it just makes it so i dont have to worry about conflicts while working on a feature.

I switched over to Superset from Conductor a few months ago and haven't looked back - it's really nice to be able to use the native Codex/Claude Code TUIs without any of the bloat

Can't wait to see what else you guys cook up!

Glad to hear it thanks for the support!