TuriX-CUA

TuriX · Desktop Actions, Driven by AI

Talk to your computer, watch it work.

📞 Contact & Community

Join our Discord community for support, discussions, and updates:

Or contact us with email: contact@turix.ai

TuriX lets your powerful AI models take real, hands‑on actions directly on your desktop.
It ships with a state‑of‑the‑art computer‑use agent (passes > 68 % of our internal OSWorld‑style test set) yet stays 100 % open‑source and cost‑free for personal & research use.

Prefer your own model? Change in config.json and go.

Table of Contents

• 📞 Contact & Community
• 🖼️ Demos
• ✨ Key Features
• 📊 Model Performance
• 🚀 Quick‑Start (macOS 15)
  • 1. Download the App
  • 2. Create a Python 3.12 Environment
  • 3. Grant macOS Permissions
    • 3.1 Accessibility
    • 3.2 Safari Automation
  • 4. Configure & Run
• 🤝 Contributing
• 🗺️ Roadmap

---

🖼️ Demos

MacOS Demo

Book a flight, hotel and uber.

Search iPhone price, create Pages document, and send to contact

Generate a bar-chart in the numbers file sent by boss in discord and insert it to the right place of my powerpoint, and reply my boss.

Windows Demo

Search video content in youtube and like it

MCP with Claude Demo

Claude search for AI news, and call TuriX with MCP, write down the research result to a pages document and send it to contact

---

✨ Key Features

Capability	What it means
SOTA default model	Outperforms previous open‑source agents (e.g. UI‑TARS) on success rate and speed on Mac
No app‑specific APIs	If a human can click it, TuriX can too—WhatsApp, Excel, Outlook, in‑house tools…
Hot‑swappable "brains"	Replace the VLM policy without touching code (config.json)
MCP‑ready	Hook up Claude for Desktop or any agent via the Model Context Protocol (MCP)

---

📊 Model Performance

Our agent achieves state-of-the-art performance on desktop automation tasks:

For more details, check our report.

🚀 Quick‑Start (macOS 15)

We never collect data—install, grant permissions, and hack away.

0. Windows Users: Switch to the windows branch for Windows-specific setup and installation instructions.

git checkout windows

1. Download the App

For easier usage, download the app

Or follow the manual setup below:

2. Create a Python 3.12 Environment

Firstly Clone the repository and run:

conda create -n turix_env python=3.12
conda activate turix_env        # requires conda ≥ 22.9
pip install -r requirements.txt

3. Grant macOS Permissions

3.1 Accessibility

1. Open System Settings ▸ Privacy & Security ▸ Accessibility
2. Click ＋, then add Terminal and Visual Studio Code ANY IDE you use
3. If the agent still fails, also add /usr/bin/python3

3.2 Safari Automation

1. Safari ▸ Settings ▸ Advanced → enable Show features for web developers
2. In the new Develop menu, enable
   • Allow Remote Automation
   • Allow JavaScript from Apple Events

Trigger the Permission Dialogs (run once per shell)

# macOS Terminal
osascript -e 'tell application "Safari" \
to do JavaScript "alert(\"Triggering accessibility request\")" in document 1'

# VS Code integrated terminal (repeat to grant VS Code)
osascript -e 'tell application "Safari" \
to do JavaScript "alert(\"Triggering accessibility request\")" in document 1'

Click "Allow" on every dialog so the agent can drive Safari.

4. Configure & Run

4.1 Edit Task Configuration

[!IMPORTANT]
Task Configuration is Critical: The quality of your task instructions directly impacts success rate. Clear, specific prompts lead to better automation results.

Edit task in examples/config.json:

{
    "agent": {
         "task": "open system settings, switch to Dark Mode"
    }
}

4.2 Edit API Configuration

Get the key for free from our official web page.
Login to our website and the key is at the bottom.

Edit API in examples/config.json:

"llm": {
      "provider": "turix",
      "api_key": "YOUR_API_KEY",
      "base_url": "https://llm.turixapi.io/v1"
   }

4.3 Configure Custom Models (Optional)

If you want to use other models not defined by the build_llm function in the main.py, you need to first define it, then setup the config.

main.py:

if provider == "name_you_want":
        return ChatOpenAI(
            model="gpt-4.1-mini", api_key=api_key, temperature=0.3
        )

Switch between ChatOpenAI, ChatGoogleGenerativeAI and ChatAnthropic base on your llm. Also change the model name.

4.4 Start the Agent

python examples/main.py

Enjoy hands‑free computing 🎉

🤝 Contributing

We welcome contributions! Please read our Contributing Guide to get started.

Quick links:

• Development Setup
• Code Style Guidelines
• Testing
• Pull Request Process

For bug reports and feature requests, please open an issue.

🗺️ Roadmap

Quarter	Feature	Description
2025 Q3	✅ Windows Support	Cross-platform compatibility bringing TuriX automation to Windows environments (Now Available)
2025 Q3	✅ Enhanced MCP Integration	Deeper Model Context Protocol support for seamless third-party agent connectivity (Now Available)
2025 Q4	Next-Gen AI Model	Significantly improved reasoning and task execution capabilities
2025 Q4	Planner	Understands user intent and makes step-by-step plans to complete tasks
2025 Q4	Workflow Automation	Record, edit, and replay complex multi-step automation sequences
2026 Q1	Offline Model Option	Fully local inference for maximum privacy and zero API dependency
2026 Q1	Persistent Memory	Learn user preferences and maintain task history across sessions
2026 Q2	Learning by Demonstration	Train the agent by showing it your preferred methods and workflows
2026 Q2	Windows-Optimized Model	Native Windows model architecture for superior performance on Microsoft platforms