A Browser Built for Browser Automation

Name: A Browser Built for Browser Automation
Availability: InStock
Author: theahura

by theahura·Jun 21, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainShip It

CDP-based agent control beats screenshot approaches—finally efficient browser automation.

Strengths

•Direct Playwright CDP scripting instead of slow vision-based mouse control
•Human-in-the-loop workflow: browse normally, delegate tasks to agent
•Transparent and debuggable—agent scripts are visible Playwright commands

Weaknesses

•Author admits it's rough around the edges with limited polish
•Niche audience—only matters if you're building browser automation agents

Post Description

Well, calling it a browser is a bit of a stretch I suppose. It's really just chromium + playwright with a terminal screen bolted on.

But damn does this thing actually work. I've tried every other kind of browser use agent and they all try to get the model to use websites by taking screenshots and moving the mouse around. Which is slow and inefficient and expensive too. By contrast I've used this browser to do things like scrape thousands of pictures or automatically configure fly.io billing for 100 orgs, while playing slay the spire in the foreground.

It's very rough around the edges, but hopefully other people find it useful!