HN Explorer

Show HN: Sculptor – A UI for Claude Code (imbue.com)

176 points by thejash ↗ HN
Hey, I'm Josh, cofounder of Imbue. We built Sculptor because we wanted a great UI for parallel coding agents.

We love Claude Code, but wanted to solve some of the problems that come from running multiple agents in parallel (ex: merge conflicts with multiple agents, reinstalling dependencies with git worktrees, Claude Code could deleting your home directory, etc).

Sculptor is a desktop app that lets you safely run Claude Code agents by putting them in separate docker containers. This lets you use Claude without having to compromise on security or deal with annoying tool permission prompts. Then you can just tell Claude to keep running the code until it actually works.

To help you easily work with containerized agents, we created “Pairing Mode”: bidirectionally sync the agent’s code into your IDE and test/edit together in real time. You can also simply pull and push manually if you want.

We have some more cool features planned on our roadmap that are enabled by this approach, like the ability to “fork” conversations (and the entire state of the container), or roll back to a previous state.

It’s still very early, but we would love your feedback.

Sculptor itself is free to use, so please try it out and let us know what you think!

49 comments

[ 4.2 ms ] story [ 83.7 ms ] thread
bfogelman
Member of the team here, happy to answer questions. Took a lot of ups, downs and work to get here but excited to finally get this out. Even more excited to share other features we've been cooking behind the scenes. Give it a try and let us know what you think, we're hungry for feedback.
thadd3us
Really proud to be a part of this team! And really excited for the future of Sculptor -- it has quickly become my favorite agentic coding tool because of the way it lets you safely and locally execute untrusted LLM code in an agentic loop, using a containerized environment that you control!
micimize
Exciting stuff! A big step towards an accelerated AI-assisted SWE approach that avoids the trap of turning engineers into AI slop janitors
dalejh
Congrats on the launch Imbue team!

I used Sculptor to build most of https://lingolog.app/ (featured in this post).

It was a blast - I was cooking dinner and blasting out features, coming back to see what Sculptor had cooked up for me in the meantime. I also painted the landing page in procreate while Sculptor was whirring away.

Of course, this meant that my time shifted from producing code to reviewing code. I found the diffs, Sculptor's internal to-do list, and summaries all helpful to this end.

n.b. I'm not affiliated with the team, but I've worked with some Imbue team members many years ago which led to being a beta tester.

rsyring
> Sculptor is free while we're in beta.

Ok, and then what? Honest question.

lrobinovitch
Been fortunate to get to try out Sculptor in pre-release - it's great. Like claude code with task parallelism and history built in, all with a clean UI.
warthog
Wasn't imbue training models for coding having raised a huge fund? Is this a pivot?
ajanuary
Unfortunately the page repeatedly crashed and reloads on my iPhone 13 mini until it gives up.
55555
Just adding that on my iPhone 13 Pro it works fine.
jMyles
So... are we all just working on various ways of using Claude Code in docker with git worktrees? Is that like, the whole world's project this month? :-)
cygn
haven't seen the other projects. What's the best one?
meowface
Looks good. Does the app have a dark theme option?
mangonomnom
got to try this a bit and really liked the UI! It felt very transparent and understandable even for someone without a coding background
_1tem
It's not clear to me what a "container" and "pairing" is in this context. What if my application is not dockerized? Can Claude Code execute tests by itself in the context of the container when not paired? This requires all the dependencies, database, etc. - do they all share the same database? Running full containerized applications with many versions of Postgres at the same time sounds very heavy for a dev laptop. But if you don't isolate the database across parallel agents that means you have to worry about database conflicts, which sounds nasty.

In general I'm not even sure if the extra cognitive overload of agent multiplexing would save me time in the long run. I think I still prefer to work on one task at a time for the sake of quality and thoroughness.

However the feature I was most looking forward to is a mobile integration to check the agent status while away from keyboard, from my phone.

stpedgwdgfhgdd
You can use git worktree to work in parallel in multiple terminal tabs. It does give a higher cognitive load.
kspacewalk2
How soon is Sculptor for Mac (Intel) coming? Excited to try it, but still hanging on to my last x86 MBP.
millanjp
This is awesome, I love how it lets claude code "go rogue" safely inside a container. I don't like how agents can screw with my filesystem so this isolation is good
cchance
Silly question but what about GPT? it feels like with the experimental api that most of the clients added for interacting the the cli clients it should be possible for something like this to run for gpt, claude, or gemini no?
mentalgear
Based on vibekit (open source) ?

"VibeKit is a safety layer for your coding agent. Run Claude Code, Gemini, Codex — or any coding agent — in a clean, isolated sandbox with sensitive data redaction and observability baked in."

https://docs.vibekit.sh/cli

cma
It might be possible to ask claude to write a claude code hook to take a docker snapshot after each finished answer with vibekit to avoid deeply integrating with another third party.
kuroko
Congrats, looks good! Lacks an option to configure anthropic base url though, hope you will add something to configure env variables
bfogelman
ooh this is a great idea -- thanks for sharing!
thejash
I haven't tried it, but it might work if you set the env var yourself (I think you can create a `.env` file in `~/.sculptor/.env` and it will be injected into the environment for the agent)

I'd give it a good 20% chance of working if you set the right environment variables in there :) Feel free to experiment in the "Terminal" tab as well, you can call claude directly from there to confirm if it works.

kate_dirky
Congrats on the launch! Looks awesome