Show HN: Open-Source Animal Crossing–Style UI for Claude Code Agents

https://github.com/outworked/outworked/releases/tag/v0.3.0
We posted here on Monday and got some great feedback. We’ve implemented a few of the most requested updates:

- iMessage channel support (agents can text people and you can text agents) Other channels are simple to extend. - A built-in browser (agents can navigate and interact with websites) - Scheduling (run tasks on a timer / cron/ in the future) - Built in tunneling so that the agents can share local stuff with you over the internet - More robust MCP and Skills support so anyone can extend it - Auto approval for agent requests

If you didn’t see the original:

Outworked is a desktop app where Claude Code agents work as a small “team.” You give it a goal, and an orchestrator breaks it into tasks and assigns them across agents.

Agents can run in parallel, talk to each other, write code, and now also browse the web and send messages.

It runs locally and plugs into your existing Claude Code setup.

Would love to hear what we should build next. Thanks again!

Comments

SkidaddleMar 27, 2026, 10:04 PM
I like the visualization, but in terms of orchestration, how does it compare to CC’s built in agent swarms?
ZeidJMar 27, 2026, 10:12 PM
Great question! It actually takes advantage of the sub-agent swarms since it is directly connected to your Claude Code instance.

We want to implement agent teams as well, but it is still an experimental Claude Code feature. So it's more of a secondary priority right now.

robonotMar 27, 2026, 9:57 PM
The parallel agent coordination is what makes this interesting. Most agent wrappers are just single-agent loops with extra steps.
ZeidJMar 27, 2026, 10:09 PM
Yes, we actually added it because we were getting impatient with how long some implementations were taking. Appreciate this comment - thank you!
FinnoidMar 27, 2026, 9:31 PM
Love this! AI agents can be so abstract to many people and this project really makes it feel much more approachable. Makes me think of Game Dev Story! Would be awesome to see little thinking bubbles over them to show what they are doing. Ultimately I see promise in making it easier to visually see what is happening in the system.
xybernetexMar 27, 2026, 10:10 PM
As a visual-oriented person I can completly agree. Being able to visualze makes things make so much more sense.
ZeidJMar 27, 2026, 9:34 PM
Completely agree, we found it helped explaining it to our non-technical friends as well.

We do have thinking bubbles but they only show up based on the task the agent is doing. Perhaps we'll add a toggle or something to give people the option to have them always on.

hamuraijackMar 27, 2026, 7:53 PM
"animal crossing-style" is a bit of a stretch
smileybarryMar 27, 2026, 8:30 PM
Yeah, I was expecting something like the Animal Crossing dialog bubble or something. At least put Tom Nook as the boss character.
ZeidJMar 27, 2026, 8:40 PM
This is such a good idea. A nondescript non-copyright infringing raccoon character as "The boss" would be perfect.
ZeidJMar 27, 2026, 7:56 PM
yeah.. maybe should have said "inspired by"
odstMar 27, 2026, 8:16 PM
Not even. Maybe briefly saw an advertisement, but didn't click it.
ZeidJMar 27, 2026, 9:00 PM
tbh just looked at the cover you know?
james-clefMar 27, 2026, 8:45 PM
Maybe a bit of an odd one, but can you decorate the office? I'm wondering like have you abstracted the decor elements into something that is straightforward to extend? How easily could I give my office a new espresso machine or something?
ZeidJMar 27, 2026, 8:51 PM
This is a fun question. The answer is yes, you can redecorate and move things around.

Right now it's all built in phaser, and furniture is pretty straight forward to build and deploy. But it requires modifying the source. We want to add support for easy drop in decoration in future updates.

adshotcoMar 27, 2026, 8:43 PM
The group-based orchestration approach is smart — having agents work on different files in parallel within a group, then passing to the next group, sidesteps a lot of the merge conflict pain you'd get from naive concurrent file edits. Curious how it handles the case where Agent A's changes to module X break the interface that Agent B in the same group expects from module Y. Do you do any kind of dependency analysis before assigning tasks to groups, or is it purely based on file-level separation?

The deny list for auto-approval is a pragmatic solution. In practice I've found the hard part isn't blocking obviously dangerous commands like rm -rf, it's the long tail of commands that are safe in one context but destructive in another (e.g. git checkout on a file with unstaged changes). Would be interested to know if you're tracking which auto-approved commands end up causing issues to refine the defaults over time.

ZeidJMar 27, 2026, 9:12 PM
Right now purely file level. But the dependency analysis is really intelligent and we'll figure out what that would look like.

The long-tail point is true. We don't do any tracking in our implementation, but we've been trying hard to refine our total our total permissions approach to think about more edge cases such as this, while not being too annoying. We think this is a general tricky issue with AI alignment ('do what I mean not what I say').

braden-lkMar 27, 2026, 10:09 PM
Sorry, but there's not even a single hint of a visual relationship to Animal Crossing here. I believe this title is inaccurate.
ContrailsMar 27, 2026, 9:10 PM
Haha this is really cool! I imagine it would be a nice tool to teach kids about working with agents.
ZeidJMar 27, 2026, 9:13 PM
This is a really neat idea, we hadn't thought about the education angle. Thanks for sharing!
mitul005Mar 27, 2026, 7:12 PM
iMessage is the one that changes the category for me. "Agents that can text real people" is a different thing than a multi-agent demo. I've been hacking on something similar and the hardest problem wasn't orchestration it was figuring out when to bother a human vs. just deciding. How does auto-approval work, is it all-or-nothing or per task?
ZeidJMar 27, 2026, 7:34 PM
There are two levels of auto approve, first level is auto-edit which is basic read and write, and basic bash tools (these can be configured to be any arbitrary bash command).

The second level is called auto approve and is for more complex bash commands. Generally the model will ask permission before running one of these big commands, but you can allow all. Right now, it's global across the instance, but we're working on making it more granular.

Also, there is a deny list of certain commands which you can customize to prevent bad behavior (like rm -rf, etc...)

We want to wire the approval process to imessage or whatever channel, but we need to first auth the imessage session to make sure it's coming through from the owner and not someone else communicating through the same channel.

jameschaearleyMar 27, 2026, 7:00 PM
Love the pixel office. Such a fun way to make multi-agent work less abstract. Being able to actually watch agents walk to their desks and pick up tasks makes it way easier to follow what's happening than staring at terminal logs. Curious if the orchestrator handles cases where two agents need to edit the same file.
ZeidJMar 27, 2026, 7:37 PM
Thank you James, great question! Generally, when the orchestrator assigns parallel work it does it in groups, with everyone in the group working on different files. When the group is done it passes the work to the next group which can then edit those same files.

We're working on simultaneous editing of the same files using git, but we want to ensure changes are merged in an intelligent way.

Ryand1234Mar 27, 2026, 9:15 PM
this seems interesting. Will give it a spin this weekend.
ZeidJMar 27, 2026, 9:15 PM
Thank you - let us know if you have any feedback. Appreciate you trying it out.
billconanMar 27, 2026, 5:53 PM
does it use the claude code api or the claude code cli? You know, the claude code api is more expensive.

I also hope it can have a webapp version, rather than electron. because most of our work are on a remote server.

ZeidJMar 27, 2026, 5:57 PM
It actually uses the Claude code SDK so it plugs into whatever you already have.

It can use API/CLI or even if you have a private hosted instance.

We're actually working on a remote web app version but its a little trickier to wire up.

These are great questions - thank you!

linsysMar 27, 2026, 8:39 PM
If it uses the SDK then it's token burn? Or can it "legally" use your Claude.ai MAX account, your subscription account?
ZeidJMar 27, 2026, 8:47 PM
Great question - we're going to look into this in-depth.
techgnosisMar 27, 2026, 9:21 PM
Not allowed? This is easy to find in the Agent SDK docs

"Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products, including agents built on the Claude Agent SDK. Please use the API key authentication methods described in this document instead."

https://platform.claude.com/docs/en/agent-sdk/overview

ZeidJMar 27, 2026, 10:08 PM
We saw this, but thought it was for Agents calling the API directly. Outworked is just a wrapper around your CLI using the existing agents and sub-agents in your Claude Code installation.

It's a great point though and we'll need to read into this more in-depth. Appreciate you raising this.

gwilkesMar 27, 2026, 10:02 PM
Right, pretty sure people got their accounts shut down for doing this kinda thing in the early days of OpenClaw before it was renamed and when it supported login. I guess you can take your chances but API is probably the only safe way to use this.
tusuegraMar 27, 2026, 9:02 PM
[dead]
lanxevo3Mar 27, 2026, 9:15 PM
[flagged]
ZeidJMar 27, 2026, 9:24 PM
That's a great heuristic. We'll definitely have to implement something like this. Thank you for this!
lanxevo3Mar 27, 2026, 9:30 PM
[dead]