ServiceNow/AgentLab

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

72
/ 100
Verified

This is a framework for researchers and developers working on AI agents that can interact with websites. It helps you build, test, and compare how well these 'web agents' perform on various online tasks. You feed in your experimental web agents and get back performance benchmarks, helping you understand their strengths and weaknesses across different web environments.

530 stars. Actively maintained with 1 commit in the last 30 days. Available on PyPI.

Use this if you are a researcher or developer focused on advancing the capabilities of AI agents that can browse and interact with websites, and you need a robust way to evaluate their performance at scale.

Not ideal if you are looking for a ready-to-use consumer product or an AI assistant for personal use, as this is a research and development framework.

AI Agent Development Web Automation Agent Benchmarking AI Research Large Language Models
Maintenance 13 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 24 / 25

How are scores calculated?

Stars

530

Forks

108

Language

Python

License

Last pushed

Feb 10, 2026

Commits (30d)

1

Dependencies

24

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/ServiceNow/AgentLab"

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