Letting Claude automate fleets of browser sandboxes

Name: Letting Claude automate fleets of browser sandboxes
Availability: InStock
Author: huss97

by huss97·Mar 3, 2026·6 points·1 comment

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemBig Brain

Bridges Claude agents to cloud browsers—solves captcha/scaling, but reworks existing agent-browser CLI.

Strengths

•Directly unblocks Claude from captcha-gated tasks by routing through proxied sandboxes
•Parallel background execution means agents don't block waiting for browser I/O
•First-shot working demo shows genuine integration, not vaporware

Weaknesses

•Crude implementation: directly embeds agent-browser binaries and routes via TS parser, minimal novel architecture
•Niche audience: only useful if you're already running Claude agents that need web access at scale

Post Description

Hey HN, wanted to share this cli and skill I built @ Steel (I'm the founder)

I was trying to set up openclaw on railway and quickly bumped up against issues with a lack of browser access, a core component of the system. Agents like OpenClaw and CC are super good at using browsers but, similar to code sandboxes, they should be able to control these browser in the background, in parallel, without getting blocked by captchas.

So I reworked agent-browser, the most popular cli for browser agents, to navigate Steel cloud browser sessions to they can run at scale and unhindered.

It's a relatively crude implementation right now as we just embed agent-browser's binaries directly into the CLI and have a higher-level TS parser to route/modify commands, but it works surprisingly well; the demo video in the link worked first shot, I just copied/pasted for the video.

GitHub Repo: https://github.com/steel-dev/cli/

Would love any feedback or thoughts on what capabilities you'd like to see shipped here!