🖥️ Control your local mouse, keyboard, and capture screenshots with the Qwen3 GUI agent driver for seamless computer use on an OpenAI-compatible endpoint.

🚀 Generate realistic GUI trajectories using GUI-ReWalk, a framework that enhances automation through reasoning and diverse, high-quality data synthesis.

🎥 Capture screen recordings and interactions on macOS, including inputs and accessibility data, to create datasets for AI model training and evaluation.

💻 Control AI agents to automate tasks on computers, enabling true autonomy with browser, terminal, and desktop interaction. Perfect for developers.

🤖 Manage AWS infrastructure intelligently using natural language with this AI-powered agent. Perfect for testing in development environments.

🌐 Explore AI-Infra to visualize the AI infrastructure landscape and discover a structured learning path for building in the cloud-native ecosystem.

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 🐙

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

CUGA is an open-source generalist agent for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

Driving all platforms UI automation with vision-based model

This is the official website for TuriX Computer-use-Agent

Agent Framework For Fintech and Banks

Agent-sandbox is an enterprise-grade ai-first, cloud-native runtime environment for AI Agents. Allows Agents to securely run untrusted LLM-generated Code, Browser use, Computer use, and Shell commands etc. with stateful, long-running, multi-session and multi-tenant.

Agent S: an open agentic framework that uses computers like a human

Fara-7B: An Efficient Agentic Model for Computer Use

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Powered by BoxLite - embeddable sandbox with hardware-level isolation and no daemon. The SQLite of sandbox, coming soon as open source.

Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas, Perplexity Comet, Dia and Microsoft CoPilot Edge Browser

🕵 Code for our EMNLP 2025 Main paper: "FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games"