OSWorld is an open-source synthetic world environment designed for embodied AI research and multi-agent learning. It provides a richly simulated 3D world where multiple agents can interact, perform tasks, and learn complex behaviors. OSWorld emphasizes multi-modal interaction, enabling agents to process visual, auditory, and symbolic data for grounded learning in a simulated world.

Features

  • Simulates a rich 3D world for embodied multi-agent learning
  • Supports multiple sensor modalities including vision and sound
  • Designed for large-scale training of autonomous AI agents
  • Includes complex interaction and collaboration tasks
  • Fully customizable environments and agent properties
  • Supports integration with reinforcement learning and language models

Project Samples

Project Activity

See All Activity >

License

Apache License V2.0

Follow OSWorld

OSWorld Web Site

Other Useful Business Software
Custom VMs From 1 to 96 vCPUs With 99.95% Uptime Icon
Custom VMs From 1 to 96 vCPUs With 99.95% Uptime

General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.

Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of OSWorld!

Additional Project Details

Programming Language

Python

Related Categories

Python Reinforcement Learning Frameworks

Registered

2025-03-13