Most AI browsers hide what the agent is doing. I wanted to see it happen live, and run it locally. So I built one.
Agents are everywhere now.
They browse, click, fill forms, buy things, take actions on your behalf.
But most of that happens somewhere you can't see.
The agent runs in the cloud. You get a summary after the fact. If something goes wrong, you find out too late.
I ran into this problem myself while using agents for my own work.
So I built Pickle.
Pickle is a browser made for AI agents, where every action shows up on screen as it happens.
The idea is simple:
Give the agent an instruction → Agent acts → you watch it happen and can step in anytime
Pickle also runs local models out of the box, so no API key is needed to get started.
As a side effect of how it feeds pages to the agent, it reduces token usage. I'm seeing about 32x less in my own sessions.
I'm building this solo, and I'd rather put it in front of real people now than keep polishing it by myself for another month. So expect some problems along the way. I'd rather find them now, with your help, than keep guessing on my own.
I'm especially interested in hearing from founders and builders who've hesitated to give an agent real access because they couldn't see what it was doing.
What would it take for you to trust an agent with real tasks?
- More visibility?
- Approval controls before risky actions?
- Just time and track record?
- Something else?
I'd love to know what actually matters to the Indie Hackers community.
Download Pickle for free here:
https://picklebrowser.com/
What stands out to me is the visibility aspect. I think the biggest barrier to wider agent adoption isn't necessarily capability, but trust; especially when an agent can take actions that are difficult to reverse.
Being able to watch the agent work and step in before a risky action could make a big difference. I'd be interested to see how you handle permissions for things like purchases, account changes, or submitting forms. A clear “approval required” layer could be just as important as the visual interface itself.
Visibility gets you the demo; it doesn't get you the daily. Watching costs attention linearly — the first week you watch every step, and the moment the agent is actually useful you stop, which is exactly when you'd want to be looking. What made me comfortable handing over real tasks was auditable after-the-fact receipts (what it called, with what arguments, what came back) plus a hard gate on the irreversible subset: send, pay, delete. Everything else runs unattended. Live view is for debugging, receipts are for trust.
One thing worth designing while it's still cheap: a local browser on the user's real profile inherits every session cookie they have, so your page representation is the sharp edge. If a snapshot fires right after a login form is filled, the password field's value lands in the model's context verbatim. Mask on serialization, not on render.
On the 32x — is that measured against raw DOM or against screenshots? And does it hold once the conversation is long, or is the page the small half of the bill by step 20?
The “watch it happen” part is a clear contrast with agents that operate out of sight. Curious which part people react to most when they see Pickle in action.