niuzaisheng/ScreenAgent
Agent controls computers through visual language models
View on index · View in 3D Map
Related repos
- Controls computers through natural language
- Browser agent for planning and executing tasks via natural language
- Open-source agent for automating GUI tasks using screenshots as input, built by ByteDance
- Browser automation via natural language instructions
- Framework for agents to use computers and code
- AI agent automates tasks and boosts productivity on your desktop
- Autonomous agent for debugging web interfaces
- vision-based agent automates browser tasks like a human
- Visualizes AI agents as characters in a virtual office
- Visual feedback tool for AI coding agents
