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

python lightweight automation gemini desktop-automation task-automation browser-automation skill-tree claude computer-control autonomous-agent ai-agent llm-agent memory-system self-evolving

• Updated Nov 6, 2026
• Python

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.

ai gcc multimodality vlm cradle computer-control lmm grounding ai-agent large-language-models llm generative-ai vision-language-model ai-agents-framework general-computer-control personoid foundation-agent

• Updated Nov 7, 2024
• Python

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

c-sharp alexa dropbox amazon-echo assistant applet ifttt google-home amazon-alexa google-assistant acc computer-control assistant-computer-control

• Updated Oct 30, 2025
• C#

MCP server for Windows OS automation

windows ai computer-vision mcp claude computer-control os-automation

• Updated Dec 2, 2025
• TypeScript

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

electron mcp developer-tools computer-control chatgpt chatgpt-web local-ai ai-coding model-context-protocol repository-automation coding-agent agent-harness chatgpt-harness

• Updated Nov 8, 2026
• JavaScript

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.

react python open-source threejs automation privacy typescript knowledge-graph speech-recognition jarvis zen-mode computer-control rag ai-assistant llm local-ai openrouter desktop-ai ai-companion plugin-marketplace

• Updated Nov 12, 2026
• Python

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

agent mobile desktop gui-automation computer-control

• Updated Jun 4, 2025
• HTML

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

text-to-speech offline-first chatbot personal-assistant jarvis usb-drive computer-control privacy-focused ai-assistant llm ollama qwen offline-ai portable-ai

• Updated Jun 6, 2026
• PowerShell

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.

python windows linux oauth remote-control mcp cybersecurity developer-tools desktop-automation browser-automation ai-agents claude computer-control chatgpt ai-agents-automation mcp-server mcp-tools

• Updated Oct 20, 2026
• Python

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

python opencv computer-vision gui-application speech-to-text gesture-recognition pyautogui computer-control third-year-project virtual-mouse mediapipe

• Updated Nov 7, 2025
• Python

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

agent toolset simplicity computer-control project-base vision-ai local-ai

• Updated Jan 3, 2026
• Python

Identification and Computer Control of a Flexible Robot Arm Joint.

design-systems matlab modeling control-theory computer-control

• Updated Dec 28, 2017
• MATLAB

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

rust keyboard screenshot automation mcp json-rpc mouse gui-automation computer-control mcp-server

• Updated Nov 2, 2026
• Rust

An offline voice assistant for Windows that actually drives the computer: windows, files, clipboard, power. Needle 3 on-device, or your own API key.

windows rust tts whisper voice-assistant windows-automation on-device computer-control wake-word sherpa-onnx needle3

• Updated Oct 28, 2026
• Rust

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

agpl desktop-automation community-edition computer-control ai-agent

• Updated Sep 24, 2026
• JavaScript

🤖 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

python windows text-to-speech automation speech-recognition llama voice-control desktop-assistant computer-control privacy-focused ai-assistant pyqt6 ollama offline-ai

• Updated Jul 21, 2026
• Python

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

chrome-devtools powershell mcp desktop-automation browser-automation codex windows-automation claude computer-control dynamic-control playwright computer-use

• Updated Apr 24, 2026
• Python

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

uiautomation windows-automation computer-control koboldcpp agentic-ai desktop-agent qwen3 telegram-bot-ai-assistant local-llm-agent

• Updated Aug 7, 2026
• Python

Hierarchal MultiModel AI Agentic Orchestration Platform - 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.

cli intelligence ocr computer-vision sandbox osiris autonomous-agents desktop-assistant long-short-term-memory computer-control episodic-memory failure-recovery ai-tools ai-agent tool-calling vibecoding coding-agent procedural-memory typesafe-jev

• Updated Nov 4, 2026
• TypeScript

进一步提升 AI 的手：看一眼屏幕，点一下按钮。零 key、零框架，命令行直用，也能当 agent 插件。

python windows screenshot automation gui-automation ai-agents computer-control

• Updated Nov 12, 2026
• Python