Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

Control your computer with your Google Home or Amazon Alexa assistant!

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

MCP server for Windows OS automation

Official Repo of "AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants"

Identification and Computer Control of a Flexible Robot Arm Joint.

qwen3-vl-2b-instruct performing step by step tasks confirming normalized coordinations usage and tools executions

The virtual application to control the desktop using hand gestures and through mobile screen.

🤖 Zox AI - Your Offline AI Desktop Assistant | Fully offline Windows AI assistant powered by Ollama + Llama 3.1 8B | Voice control, computer automation, 100% privacy

Autonomous AI agent for Windows - control your browser, files, Excel and terminal using natural language, powered by Groq LLMs (llama-3.1-8b + llama-3.3-70b) with automatic model selection.

Gesture control system for PC using Arduino UNO, ultrasonic sensors, and Python automation.

An AI assistant for cross-device control, automating actions seamlessly between devices.

电脑遥控器

Official Repository of "A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions"

🎤 Controle seu computador via Alexa com comandos de voz em português! Wake-on-LAN, shutdown seguro, verificação de status. Complete Alexa skill for computer control with Portuguese voice commands.

Computer Measurement and Control Course Spring 2021 - Sharif University of Technology

OpenClaw is a powerful AI agent that takes full control of your PC – moves mouse, types, clicks, browses, installs software, and completes any task autonomously. No API keys required. Works with local LLMs (Llama, Mistral) or cloud (GPT-4, Claude).

Helix Control: a Windows computer-use stack for MCP agents across browser, desktop, and dynamic UI automation

Memory Hive extension for owner-approved agent control, proof, and safety gates.