
From manual steps to automated tests in minutes.
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.
- 🌟 Overview
- ✨ Key Features
- 📥 Getting Started
- 🖥️ Automation Modes
- 🔍 Explore Mode
- 🤝 Contributing
- 📄 License
- 📧 Contact
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.
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
-
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
-
Download and Install
git clone https://github.com/presidio-oss/factif-ai.git cd factif-ai npm run install:all
-
Quick Setup
# Copy environment files cp frontend/.env.example frontend/.env cp backend/.env.example backend/.env # Start the application npm start
-
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:
Factifai offers two powerful modes of automation to cover all your testing needs:
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
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:
- VNC Client: localhost:5900
- Browser: http://localhost:6080
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 enables you to map and visualize web applications through AI-powered exploration and generates detailed documenation:
- 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
- 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
To contribute to the project, start by exploring open issues or checking our feature request board.
Please read our Contributing Guidelines for more details.
This project is licensed under the MIT License - see the LICENSE file for details.
Please read our Code of Conduct to keep our community approachable and respectable.
For questions or feedback, please contact us at hai-feedback@presidio.com.