computer-control

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!

MCP server for Windows OS automation

Local agency/runtime harness for ChatGPT Web: repositories, tasks, commands, validation, Git, skills/memory, observability, and opt-in computer control.

Open-source JARVIS-class desktop AI. Zen mode orb, computer control, plugin marketplace, custom tools, local RAG, knowledge graph, voice personality, automations, vision, 3D Holodeck, blackout privacy — all local, no cloud.

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

🦾 Portable Jarvis-like AI assistant that runs entirely from a USB drive - 100% offline, voice commands, computer control

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

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

Client-neutral MCP server and secure desktop Control Center for Windows/Linux computer automation, with OAuth/Bearer auth, scoped access, UI/browser control, audit logging, and remote HTTPS support.

Identification and Computer Control of a Flexible Robot Arm Joint.

面向 AI Agent 的屏幕操作 MCP 服务器 — 截图 + 鼠标键盘控制，9 个工具经 Streamable HTTP 上的 JSON-RPC 2.0 暴露

AGI-1 Community Controller — transparent step-by-step desktop-control community edition (AGPL-3.0)

🤖 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

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

Local LLM desktop agent that understands the screen and automates GUI tasks from telegram bot. [ Testing Phase ]

Hierarchal MultiModel AI Agentic Orchestration Framework - Project J.A.R.V.I.S ★ Echo Mac is engineered to be a state-of-the-art, fully autonomous agentic wrapper for your operating system. It operates at the intersection of streaming multimodal AI and deep OS integration.

Local Windows GUI automation daemon for AI agents via MCP/CLI, built for Antigravity and Cursor.

Free AI voice assistant for Windows with PC control, Gemini chat, ElevenLabs TTS and a futuristic Python HoloDesk UI.