Hiro

Let Hiro handle your testing and documentation, so you can focus on building.

View Repository · Report Bug · Request Feature

📔 Table of Contents

• About the Project
  • Tech Stack
  • Features
  • Color Reference
  • Environment Variables
• Getting Started
  • Prerequisites
  • Installation
  • Run Locally
• Usage
• Roadmap
• Contributing
  • Code of Conduct
• License
• Contact
• Acknowledgements

🌟 About the Project

Hiro is an AI tool designed to automatically generate unit test cases and requirement documentation for your codebase, regardless of the programming language or framework you're using.

👾 Tech Stack

• Backend: Python 3.x
• AI/ML: LangChain, Groq (Llama 3.3 70B), Google Generative AI
• Web Framework: Streamlit
• GitHub Integration: PyGithub, GitHub API
• Environment Management: python-dotenv
• Testing: pytest, debugpy
• Dependencies: See requirements.txt for complete list

🎯 Features

• Language Agnostic: Works with any programming language or testing framework
• AI-Powered Test Generation: Uses Groq's Llama 3.3 70B model to generate comprehensive test cases
• GitHub Integration: Direct integration with GitHub repositories via PyGithub
• Repository Analysis: Automatically analyzes repository structure and file contents
• Automated Test File Creation: Creates properly named test files in organized directories
• Metadata Generation: Generates detailed metadata and package requirements for each test
• Streamlit Web Interface: User-friendly web interface for easy interaction
• Branch Management: Automatically creates and manages test branches on GitHub
• Multiple AI Models: Supports Groq and Google Generative AI for flexible AI processing

🎯 How it Works

1. Repository Analysis: Hiro connects to your GitHub repository and analyzes its file structure and contents
2. Code Context Extraction: The system extracts relevant code files, skipping binary and configuration files
3. AI Processing: The code is processed by Groq's Llama 3.3 70B model to understand functionality and generate appropriate test cases
4. Test Generation: AI generates up to 3 comprehensive test cases per file, following testing best practices
5. Metadata Creation: Each test includes metadata and required package information for easy setup
6. GitHub Integration: Tests are automatically committed to a new branch called hiro-tests on your repository

🔑 Environment Variables

To run this project, you will need to add the following environment variables to your .env file

GITHUB_PERSONAL_ACCESS_TOKEN - Your GitHub personal access token for repository access

GROQ_API_KEY - Your Groq API key for AI model access

GOOGLE_API_KEY - Your Google API key for additional AI services

🧰 Getting Started

‼️ Prerequisites

This project requires Python 3.x and pip

• Python 3.7 or higher
• pip (Python package installer)
• Git (for GitHub integration)

⚙️ Installation

1. Clone the repository

  git clone https://github.com/hanif-adedotun/hiro.git
  cd hiro

2. Navigate to the server directory

  cd server

3. Create a virtual environment (recommended)

  python -m venv .venv
  source .venv/bin/activate 

4. Install dependencies

  pip install -r requirements.txt

5. Create a .env file in the server directory and add your API keys

  touch .env 

🏃 Run Locally

1. Make sure you're in the server directory and have activated your virtual environment

  cd server
  source .venv/bin/activate 

2. Ensure your .env file contains the required API keys

  GITHUB_PERSONAL_ACCESS_TOKEN=your_github_token
  GROQ_API_KEY=your_groq_api_key
  GOOGLE_API_KEY=your_google_api_key

3. Run the application

  python app.py

4. For the Streamlit web interface, run:

  streamlit run streamlit_app.py

The application will start and you can begin generating test cases for your repositories.

👀 Usage

Command Line Interface

1. Run the main application:

python app.py

2. Follow the prompts to provide your GitHub repository URL

3. The system will automatically:

   • Analyze your repository structure
   • Generate test cases for each relevant file
   • Create organized test files in a hiro-tests directory
   • Commit the tests to a new branch on your repository

Web Interface

1. Start the Streamlit application:

streamlit run streamlit_app.py

2. Open your browser to the provided local URL (usually http://localhost:8501)

3. Use the web interface to:

   • Enter repository URLs
   • Monitor test generation progress
   • View generated test files and metadata
   • Manage your test generation workflow

🧭 Roadmap

• Basic GitHub repository integration
• AI-powered test generation with Groq
• Streamlit web interface
• Automated test file creation and organization
• GitHub branch management and commits
• Enhanced test coverage analysis
• Dashboard for test result reporting and analytics
• Integration with more AI models
• Automated documentation generation
• CI/CD pipeline integration

👋 Contributing

Contributions are always welcome!

See contributing.md for ways to get started.

⚠️ License

Distributed under the no License. See LICENSE.txt for more information.

🤝 Contact

Hanif - @devhanif - hiro@hanif.one

Project Link: https://github.com/hanif-adedotun/hiro