ServiceNow/BrowserGym

🌎💪 BrowserGym, a Gym environment for web task automation

61
/ 100
Established

This project provides a standardized testing ground for evaluating automated web agents. It allows researchers to train and test intelligent agents on a variety of web-based tasks, from simple clicks to complex workflows. The output is data on how effectively an agent performs specific browser actions, making it useful for AI researchers developing web automation and agent intelligence.

1,153 stars. Actively maintained with 2 commits in the last 30 days.

Use this if you are an AI researcher developing or evaluating web agents and need a consistent environment to test their performance on diverse browser tasks.

Not ideal if you are looking for an off-the-shelf solution to automate your own daily web browsing tasks, as this is a research framework, not an end-user tool.

AI research web agent development automation testing machine learning evaluation intelligent systems
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,153

Forks

153

Language

Python

License

Last pushed

Feb 10, 2026

Commits (30d)

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ServiceNow/BrowserGym"

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