- 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!
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.
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.
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.
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.
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').
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.
We're working on simultaneous editing of the same files using git, but we want to ensure changes are merged in an intelligent way.
I also hope it can have a webapp version, rather than electron. because most of our work are on a remote server.
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!
"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."
It's a great point though and we'll need to read into this more in-depth. Appreciate you raising this.