Skip to content

AI-powered computer control for automated testing. FactifAI uses vision models (Claude, GPT-4o, Gemini) to interact with applications naturally - clicking, typing, and verifying results just like a human would.

License

Notifications You must be signed in to change notification settings

presidio-oss/factif-ai

Folders and files

NameName
Last commit message
Last commit date

Latest commit

cab1e53 · Mar 27, 2025

History

23 Commits
Mar 27, 2025
Jan 15, 2025
Mar 18, 2025
Mar 27, 2025
Mar 26, 2025
Jan 13, 2025
Mar 14, 2025
Mar 11, 2025
Mar 25, 2025
Jan 13, 2025
Jan 13, 2025
Jan 13, 2025
Mar 11, 2025
Mar 25, 2025

Repository files navigation

License Issues Stars Forks

HAI Logo

Automate testing through AI-powered computer control.
From manual steps to automated tests in minutes.

🚀 Factifai

Factifai revolutionizes test automation by directly controlling your computer through AI. Using built-in vision capabilities of Claude, OpenAI, and Gemini along with computer use, it can navigate any application naturally - clicking, typing, and verifying results just like a human would.

Table of Contents

🌟 Overview

In today's fast-paced software development landscape, efficient testing is crucial for delivering high-quality applications. Factifai transforms how teams approach testing by combining AI vision with direct computer control, enabling natural interaction with applications.

✨ Key Features

🔮 Multi-Modal Support

Built-in support for leading vision-language models:

  • Claude: Anthropic's advanced vision and reasoning model

  • OpenAI: GPT-4o with visual understanding capabilities

  • Gemini: Google's multimodal AI for computer interaction

  • OmniParser: Screen Parsing tool for Pure Vision Based GUI Agent

🤖 AI-Powered Computer Control

  • Intelligent element detection and navigation

  • Automated verification and validation

  • Comprehensive test documentation with automated screenshot capture for each step

  • Integrated test case export with visual step-by-step documentation

📥 Getting Started

  1. Download and Install

    git clone https://github.com/presidio-oss/factif-ai.git
    cd factif-ai
    npm run install:all
  2. Quick Setup

    # Copy environment files
    cp frontend/.env.example frontend/.env
    cp backend/.env.example backend/.env
    
    # Start the application
    npm start
  3. Access the Application

    • Open http://localhost:5173 in your browser
    • Follow the setup wizard to configure your preferred AI model

For detailed configuration options, see:

🖥️ Automation Modes

Factifai offers two powerful modes of automation to cover all your testing needs:

🌐 Puppeteer Mode (Default)

Perfect for web application testing, the AI agent uses Puppeteer to control Chrome/Chromium browser:

  • Web Testing: Automate any web application
  • Form Handling: Smart form detection and interaction
  • Visual Verification: AI-powered UI validation
  • Screenshot Capture: Automated visual documentation

🎯 Docker VNC Mode

For comprehensive testing of desktop and mobile applications:

# Start the VNC environment
docker run -d \
  --name factif-vnc \
  -p 5900:5900 \
  -p 6080:6080 \
  factif-ubuntu-vnc

Access via:

Features:

  • Desktop Apps: Test any desktop application
  • Mobile Testing: Use emulators for mobile apps
  • Cross-Platform: Test across different platforms
  • Full Control: Complete system automation

🔍 Explore Mode

Explore Mode enables you to map and visualize web applications through AI-powered exploration and generates detailed documenation:

Features

  • Interactive Mapping: Automatically detect and visualize any website structure
  • Element Detection: AI identifies clickable elements like buttons, links, and navigation items
  • Route Classification: Smart categorization of different application pages and routes
  • Visual Graph: Interactive visualization of application architecture and navigation paths along with detailed documentation

Key Benefits

  • Accelerated Discovery: Quickly understand a new applications without manual exploration of all the pages
  • Visual Documentation: Automatically generate visual maps of application structure
  • Enhanced Testing: Use discovered paths to create comprehensive test scenarios

🤝 Contributing

To contribute to the project, start by exploring open issues or checking our feature request board.

Please read our Contributing Guidelines for more details.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

📜 Code of Conduct

Please read our Code of Conduct to keep our community approachable and respectable.

📧 Contact

For questions or feedback, please contact us at hai-feedback@presidio.com.