#840 · Primary category： AI Agents & Automation
webarena
Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"
Project last updated：11/26/25
GitHub Stars
1.6K
Forks
248
Contributors
14
License
Apache-2.0
Why we included this project
WebArena gives you a real browser environment to test agents against, not a sandbox of toy API calls. It bundles a self-hosted set of realistic sites, including an e-commerce store, GitLab, a forum, maps, and Wikipedia, wrapped in an OpenAI-Gym-style interface, so you can run an agent through concrete tasks like placing an order or editing a page and get a clean pass/fail result plus recorded trajectories to study. This is the canonical implementation, so it reproduces the results from the paper, and the surrounding ecosystem now supports parallel experiments and a shared leaderboard through AgentLab and BrowserGym. For teams evaluating LLM-driven web agents, it is a practical default for benchmarking and debugging.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.