Awesome AI Agents › Desktop Automation

OpenCoworkAI/open-cowork

⭐ 1728 TypeScript repository created 2026-01-13

Open Cowork is a desktop application that packages an LLM agent runtime behind a graphical interface, distributed as one-click installers for Windows and macOS so that no development environment setup is required. It is presented as an open-source implementation of Claude Cowork and can be driven by Claude, OpenAI-compatible APIs, and Chinese models such as GLM, MiniMax and Kimi, with keys supplied by the user through OpenRouter, Anthropic or another provider. The application gives the agent a workspace folder in which it can read, write and reorganize files, and a Skills system with built-in workflows for producing and processing PPTX, DOCX, PDF and XLSX documents; users can add or delete their own skills. External capabilities are attached through MCP connectors, which let the agent reach a browser, Notion and other desktop applications. A computer-use mode allows the agent to drive graphical desktop applications directly, and the README recommends a vision-capable model for that path. Remote operation is supported through collaboration platforms such as Feishu (Lark) and Slack, so runs can be started and followed from a chat client. Multimodal input works by dragging files and images into the chat box, and a Trace panel shows reasoning steps and tool calls as they happen. Isolation is layered: a path guard confines file operations to the chosen workspace on every platform, while WSL2 on Windows and Lima on macOS route shell commands into a separate Linux virtual machine with the workspace mounted; if no virtual machine is available the commands fall back to native execution with path restrictions. The project targets users who want local agent-driven desktop automation without writing code, and it can also be built from source with Node.js.

https://github.com/OpenCoworkAI/open-cowork

desktop-agentmcpsandboxcomputer-useelectron

Also in Desktop Automation

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.

vercel-labs/agent-desktop

CLI and C library giving AI agents computer-use access to native desktop apps on macOS, Windows and Linux via the OS accessibility tree, instead of screenshots or pixel matching.

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.

iflytek/astron-rpa

AstronRPA is an enterprise-grade open-source Robotic Process Automation desktop application that enables low-code/no-code workflow automation for desktop and web applications with strong enterprise security, collaboration, and AI agent integration.