Projects using OSWorld

We thank the trust from following projects for using OSWorld to accelerate the progress of multimodal agents!

• Cradle: Empowering Foundation Agents Towards General Computer Control

• Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

• Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding

• CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents

• Windows Agent Arena: a benchmark for AI agents acting on your computer

• Agent S: An Open Agentic Framework that Uses Computers Like a Human

• Model Card Addendum: Claude 3.5 Haiku and Upgraded Claude 3.5 Sonnet

• OS-ATLAS: A Foundation Action Model For Generalist GUI Agents

• Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

• Ponder & Press: Advancing Visual GUI Agent towards General Computer Control

• Aria-UI: Visual Grounding for GUI Instructions

…