bytedance/UI-TARS-desktop
UI-TARS Desktop is a GUI Agent application that uses a Vision-Language Model to enable natural language control of computers across multiple platforms with real-time visual recognition and automation capabilities.
Awesome AI Agents › Desktop Automation
iflytek/astron-rpa
AstronRPA is an enterprise-grade Robotic Process Automation (RPA) desktop application designed to enable individuals and enterprises to automate workflows and desktop software with ease. It features a visual designer that supports low-code/no-code development, allowing users to rapidly build automation workflows for desktop applications and web pages. The project integrates deeply with Astron Agent, a native agent platform, enabling bi-directional calls between automation workflows and intelligent agent systems, which broadens the scope of business automation scenarios. The platform supports comprehensive automation across Windows desktop applications and web browsers, including popular office software like WPS and Microsoft Office, financial and ERP systems such as Kingdee and YonYou, and browsers like Internet Explorer, Edge, and Chrome. It offers over 300 pre-built atomic components covering UI operations, data processing, and system interactions, which can be visually orchestrated or extended with custom components for high flexibility and maintainability. AstronRPA is built with enterprise-grade security and collaboration features, including terminal monitoring, scheduling modes, robot team sharing, and permission control, facilitating a complete automation management ecosystem for teams. The developer-friendly environment provides an intuitive drag-and-drop interface for designing and debugging automation workflows, reducing development barriers and enabling business users to participate in automation creation. The architecture follows a frontend-backend separation model, with the frontend built using Vue 3, TypeScript, and Tauri for desktop applications, and the backend using Java Spring Boot and Python FastAPI microservices. The core engine is Python-based, integrating over 20 RPA components with support for image recognition and UI automation. The system is deployable via Docker, ensuring scalability and observability. AstronRPA supports multi-channel trigger integration, including direct execution, scheduled tasks, API calls, and MCP services, allowing flexible embedding in complex business scenarios. The project also provides extensive documentation, including user guides, deployment instructions, and API documentation, making it accessible for both technical and non-technical users. Keywords: Robotic Process Automation, RPA, automation, low-code, no-code, desktop automation, web automation, enterprise security, collaboration, workflow, visual designer, Python, Vue 3, Java Spring Boot, FastAPI, Docker, image recognition, UI automation, scheduling, API integration, Astron Agent, AI integration, cross-application automation, component-based, team collaboration, business automation.
https://github.com/iflytek/astron-rpa
Also in Desktop Automation
asweigart/pyautogui
PyAutoGUI is a cross-platform Python module that enables programmatic control of the mouse and keyboard for GUI automation, including features like screen capture and image recognition.
bytebot-ai/bytebot
Bytebot is a containerized Linux desktop environment that enables programmatic control and remote access for automation, scraping, CI tasks, and remote work through a unified REST API and VNC interfaces.
OthersideAI/self-operating-computer
The Self-Operating Computer Framework enables multimodal AI models to autonomously operate a computer by interpreting screen visuals and executing mouse and keyboard actions to achieve user-defined objectives.
wonderwhy-er/DesktopCommanderMCP
Desktop Commander MCP is a server that integrates with the Claude desktop app to provide terminal control, file system search, and diff-based file editing capabilities, enabling advanced AI-assisted desktop management.
jacklandrin/OnlySwitch
OnlySwitch is a customizable all-in-one macOS menu bar app that consolidates system toggles, shortcuts, and AI-powered controls to enhance user productivity and convenience.
yuruotong1/autoMate
autoMate is an AI-driven local automation assistant that uses natural language commands to enable users to automate complex computer tasks without programming, supporting local deployment and full interface control for enhanced privacy and flexibility.
TurixAI/TuriX-CUA
Open-source computer-use agent that performs real GUI actions on macOS and Windows desktops, with swappable vision-language model backends and MCP access for other agents.