Deliver a local, Windows-based execution layer for MCP-capable agents with zero cloud dependency and broad agent support.
Enable fast native desktop control on macOS and Windows for MCP agents using Accessibility, OCR, and Chrome CDP integration.
🖥️ Run an AI agent locally to control a virtual desktop via natural language, automating tasks without cloud dependencies using vision-language AI.
📄 Generate static question banks easily with Python and JSON for fast, SEO-friendly websites hosted on GitHub Pages.
Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.
Fara-7B: An Efficient Agentic Model for Computer Use
🖥️ Control your local mouse, keyboard, and capture screenshots with the Qwen3 GUI agent driver for seamless computer use on an OpenAI-compatible endpoint.
Claude Computer demonstrates AI autonomy in a virtual machine with real-time streaming, research, creation, and exploration. Watch Claude navigate, interact, and learn in real time 🐙
Building Blocks to automate desktop workflows end-to-end using AI
Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, internal tools. No API needed. One Docker command.
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.
This is the official website for TuriX Computer-use-Agent
Open-source AI sandbox infrastructure for code execution, browser use, and AI agents.
Your PC in your pocket — a Telegram bot for remote control, Gemini AI automation, and developer tools.
Records a workflow once. Replays it with variations you can edit like code.
Screenshot + percentage grids enabling any multimodal LLM for non-blocking RPA/Computer Use。为任意多模态大模型提供截图+百分比坐标网格，实现无感无阻塞的RPA和电脑使用
Windows desktop operator powered by Codex App Server
Build autonomous AI agents in Python.
🐧Operator-Use: AI that can do stuffs on your computer
Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
Add a description, image, and links to the computer-use topic page so that developers can more easily learn about it.
To associate your repository with the computer-use topic, visit your repo's landing page and select "manage topics."