Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目，支持在 Mac mini/MacBook 上或通过算力棒本地运行推理，实现纯视觉驱动的跨平台 GUI 自动化操作。数据完全本地处理，支持复杂多步骤任务规划与执行。

👾 Open Computer Use – Open-Source Alternative to Codex Computer Use

State of the Art 82% OSWorld Computer Using Agent, production-ready. Remote and Local! Setup using one API Key

🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/

AutoNode: A Neuro-Graphic Self-Learnable Engine for Cognitive GUI Automation

Auto-Use Computer Use — drives your OS, browser, scours the web, writes your code. One agent, end to end.

Computer Use Protocol is a universal schema for AI agents to perceive and interact with any desktop UI.

PyBreeze features built-in modules tailored for every level of modern automation, allowing developers to tackle complex scenarios without leaving the IDE.

Fully localized Robot Framework library for automating the SAP GUI using text locators

A framework for GUI automation

[ACL 2026 Main] Official repository for paper: OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents

Command Line telepathy. An Autonomous Al Agent for your Terminal that turns intent into Execution (Windows/Linux/Mac)

Nim GUI Automation Linux, simulate user interaction, mouse and keyboard.

A visual GUI automation framework for Windows and emulators. Design event-driven workflows with pixel/color matching, precise timing, and multi-instance orchestration. No-code mouse/keyboard input simulation for interactive testing.

Autonomous GUI agent — give it a task, it operates the desktop. Visual memory, one-shot UI learning. | 自主GUI代理——给它一个任务，它操作桌面。视觉记忆，一次学习即可操作。

Desktop automation library for Ruby

GUI automation toolkit for Rust

MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland -- 30 tools for virtual and live sessions

Windows backend input automation library in Go (Message + HID). A Go wrapper over Interception for reliable Windows input automation. 基于内核驱动级的 Windows RPA 自动化 输入注入库

Lightcone: SDK for computer use agents