Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/presidio-oss/factif-ai

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.
https://github.com/presidio-oss/factif-ai

anthropic automated-testing automation bedrock claude computer-use docker-vnc factif-ai gpt-4o hai human-ai omniparser puppeteer testing

Last synced: about 20 hours ago
JSON representation

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.

Awesome Lists containing this project

README

        


License
Issues
Stars
Forks







HAI Logo




Automate testing through AI-powered computer control.

From manual steps to automated tests in minutes.



# 🚀 Factif AI

**Factif AI** 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.


FACTIF-AI in action

## Table of Contents
- [🌟 Overview](#-overview)
- [✨ Key Features](#-key-features)
- [📥 Getting Started](#-getting-started)
- [🖥️ Automation Modes](#️-automation-modes)
- [🤝 Contributing](#-contributing)
- [📄 License](#-license)
- [📧 Contact](#-contact)

## 🌟 Overview

In today's fast-paced software development landscape, efficient testing is crucial for delivering high-quality applications. Factif AI 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](https://github.com/microsoft/OmniParser)**: Screen Parsing tool for Pure Vision Based GUI Agent


FACTIF-AI in action

### 🤖 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


FACTIF-AI in action

## 📥 Getting Started

1. **Download and Install**
```bash
git clone https://github.com/presidio-oss/factif-ai.git
cd factif-ai
npm run install:all
```

2. **Quick Setup**
```bash
# 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:
- [Frontend Setup Guide](frontend/README.md)
- [Backend Configuration](backend/README.md)

## 🖥️ Automation Modes

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


FACTIF-AI in action

### 🌐 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:
```bash
# 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

## 🤝 Contributing

To contribute to the project, start by exploring [open issues](https://github.com/presidio-oss/factif-ai/issues) or checking our [feature request board](https://github.com/presidio-oss/factif-ai/discussions/categories/feature-requests?discussions_q=is%3Aopen+category%3A%22Feature+Requests%22+sort%3Atop).

Please read our [Contributing Guidelines](./CONTRIBUTING.md) for more details.

## 📄 License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

## 📜 Code of Conduct

Please read our [Code of Conduct](CODE_OF_CONDUCT.md) to keep our community approachable and respectable.

## 📧 Contact

For questions or feedback, please contact us at [[email protected]](mailto:[email protected]).