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
jmerelnyc/Photo-agents
Photo Agents is a single Python package that provides a local runtime for LLM agents which operate a computer. Its design premise is that context should not be an ever-growing chat transcript: the agent takes in what is visible on screen, stores bound observations in memory layers, and writes its own reusable skills from runs that succeeded. The runtime centres on a streaming agent loop that drives any tool-calling model through a perceive, reason and act cycle. A multi-provider router supports Anthropic and OpenAI models natively and offers a mixed failover session across providers. The execution toolset is aimed at real work on the host machine: file input and output, sandboxed code execution for Python, PowerShell and bash, browser automation through a Chrome DevTools Protocol bridge, and a memory system split into working memory, global memory, standard operating procedures and a session archive. Several frontends ship with the package, including a Streamlit web application, a PyQt desktop application, a desktop companion, a service hub for starting and stopping components, and prebuilt bots for Telegram, QQ, Feishu, WeCom and DingTalk. Optional extras add Langfuse observability and a cron-style scheduler, and a reflect or watchdog mode lets a user-supplied check function trigger the next task automatically. It installs from PyPI as photoagents, needs Python 3.10 or newer, and is tested on Windows, macOS and Linux. Note one operational constraint stated in the README: the runtime is gated by a Photo Agents API key that is validated remotely, with the result cached for 24 hours, so it is not fully self-contained despite running locally. The project describes itself as beta and is MIT licensed.
https://github.com/jmerelnyc/Photo-agents
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.
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.
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.