avipeltz

agreed

If you want to do that you mine as well give Superset a try, we've put a lot of time into giving a good terminal experience, with baked in notifications and a daemon that runs in the background so your terminal sessions dont die when the app updates or closes.

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.

makes sense, well if you ever want to dabble, let us know how you like it :)

Glad to hear it! :) we'll keep shipping and making improvements

Thanks! glad to hear it :)

definitely understand the perspective. I feel like theres some dev work that completely requires me to be single threaded and just think hard, but there other modes where i can jump into whack-a-mole mode and try to work on a bunch of github issues in parallel, or sentry issues, or little ui bugs and the thinking goes more into reviewing plans and prs and i dont have to be as attentive to each individual session

ooo this could be a webgl context bug, we are working on fixing this @keit

sooooooooooooooon! nobody on the team daily drives windows yet so until we have an engineer on the team driving windows we probably wont be able to properly support it.

thanks!

yes, we do support the ability to open a folder and have superset initialize it as a git project too. Would that work for your usecase?

we're actually currently evaluating integrating acp for our chat, but when you start digging a bit deeper its not a complete silver bullet.

Glad to hear it thanks for the support!

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

hmm well we do have a slack integration and forsee a discord integration in the future so maybe we'll end up getting there for you :)

yeah there is a lot of overlap, we are more terminal first than conductor so you can do can use any cli agent you want. We have a lot more quality of life features around the terminal like notifications, and some things similar to tmux where if you kill the app or update your sessions stay alive and running. We also recently released remote workspaces so you can setup cloud workspaces for your agents. Id say if you like the chat experience conductor is still a bit more polished, we'll get to that level of polish soon, but if you care more about the terminal and cloud and more new integrations we are shipping superset is better.

glad to hear it! thank you!

yeah i think theres a lot of ux conventions that are starting to get figured out, but we do want to be different. At least right now most dont well support remote workspace, issue tracking, or review. I bet most of the current ux patterns will look very different in a year

thanks! yeah we daily drive superset so it definitely has been working for us, and yeah these tools are gonna end up looking pretty interesting :)

thanks! give it a try :) https://github.com/superset-sh/superset

isnt this just the old school way of making a static website? its nice and chill and peaceful

At least for me one of the major reasons to run an agent in a sandbox is to save memory on my machine if i am running multiple agents in parallel. Wouldnt this not help for that?

cool idea

Thanks, this is cool!

If you start leaning more on coding agents, you quickly realize there are a lot of 2–30 minute windows where you’re just waiting for an agent to implement something or finish a review. In those pockets I generally spinning up small tasks or running a few parallel experiments with different models or approaches. Once you’re juggling multiple threads having isolated working environments becomes pretty essential. We're just trying to make the environment management and that whole workflow much less of a headache. But I don't think this is the best workflow for everyone its just what we've been seeing more people converge towards.

That's a pretty interesting approach, would love to see a demo of your setup :) my email is avi@superset.sh if you're down to chat!

After setting up catnip it seems pretty sweet. The major difference is they are running as a cloud sandbox and we are currently running as a local terminal. Say you don’t want to use any worktrees or do stuff in parallel superset still works as a classic terminal. Eventually we plan on adding cloud workspaces like catnip tho

That’s what our setup/teardown scripts are for but we plan on making the generation of them automatic

we are working on that, but its not there just yet

havent tried it yet, but i just signed up so ill get back to you on that :)