bytedance/UI-TARS

Agents interacting with GUIs through vision

View on index · View in 3D Map

Related repos

• Multimodal agent for computer use
• Agent controls computers through visual language models
• Computer use agent for Linux using its own mouse and keyboard
• Agent for web and coding tasks
• Desktop studio for managing AI agents via Agent Client Protocol
• Vision-Language-Action model for GUI agents
• Framework for agents to learn from environments and interactions
• UI for managing and interacting with deep AI agents
• Reinforcement fine-tuning for UI agents