idan-rubin/browserclaw

AI-friendly browser automation with snapshot + ref targeting. Standalone wrapper around OpenClaw's browser module.

41
/ 100
Emerging

This tool helps AI agents interact with websites by providing a text-based snapshot of a web page, along with numbered references to interactive elements. An AI can read this text and then specify a reference number to click, type into, or otherwise interact with an element. It's designed for developers building AI agents or automated systems that need to navigate and extract information from websites reliably and efficiently.

Available on npm.

Use this if you are building an AI agent, platform, or automated system that needs a fast, reliable, and cost-effective way to control a web browser without relying on visual analysis or brittle CSS selectors.

Not ideal if you are looking for a complete, off-the-shelf AI agent that handles all task planning and execution within the tool itself.

AI agent development web automation data scraping bot development workflow automation
Maintenance 10 / 25
Adoption 6 / 25
Maturity 20 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

TypeScript

License

MIT

Last pushed

Mar 12, 2026

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/idan-rubin/browserclaw"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.