xlang-ai/OSWorld

3,135 534PythonApache-2.0Updated 3 weeks ago

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

agentartificial-intelligencebenchmarkclicode-generationguilanguage-modellarge-action-modelllmmultimodalnatural-language-processingreinforcement-learningrpavlm

Project homepage

Our verdict: worth borrowing ideas from

Offers a comprehensive simulated desktop environment and evaluation framework for multimodal agents, a valuable reference for building and testing the engineer's Claude‑based agent orchestration.

Similar repos

practical-tutorials/project-based-learning 273,679 · Python
NousResearch/hermes-agent 215,977 · Python
Significant-Gravitas/AutoGPT 187,064 · Python
yt-dlp/yt-dlp 178,345 · Python
microsoft/markitdown 166,660 · Python
anthropics/claude-code 141,512 · Python