This project aims to modernize legacy codebases by transforming them into modern, efficient, and maintainable code. Through an AI-driven analysis and transformation process, legacy systems can be upgraded to meet current standards and technologies.

Product demo: https://codera-ai.vercel.app/chat

Google Colab AI Prototype: https://colab.research.google.com/drive/1XaA3BmUssSqr9G4l3EeKW05fx0eOYf8V?usp=sharing

• Creates a single file (e.g., JSON) containing all code from the legacy project.

• Reads the code archive.
• Summarizes the code to create a prompt for further actions.

• Generates code suggestions based on the summary, which can either be presented as text or used to directly overwrite the existing files.

• Tailors prompts based on the user's role (Developer, DevOps) and experience.

• Manages user sessions and interactions through a web interface.

• Converts code summaries into visual representations.

• Provides written advice based on the code analysis.

1. User Registration: Users sign up on the platform and set their role and experience level.
2. Repository Upload: Users upload their GitHub repository (archive or files) to the platform.
3. Code Segmentation: The system creates a JSON file containing the entire codebase, which is then used for analysis.
4. Code Analysis: The code is analyzed by the Code Analyser, interacting with an LLM to produce a logic summary.
5. Agent Creation: Based on the logic summary, various agents (Developer, UX/UI, etc.) are created to provide specific recommendations and actions.
6. Personalized Recommendations: Users receive suggestions tailored to their role, which can be used to directly modify and update the code.

Follow these instructions to set up and run the project on your local machine for development and testing purposes.

• Node.js and npm (for the Next.js project)
• Docker (for running Dockerized services)

1. Clone the repository to your local machine.
2. Install the dependencies.

       npm install

3. Start the development server.

       npm run dev

1. Navigate to the directory containing the Server Dockerfile.
2. Build the Docker image.

       docker build -t server-image .

3. Run the Docker container.

       docker run -p 8000:8000 server-image

1. Navigate to the directory containing the LLM Dockerfile.
2. Build the Docker image.

       docker build -t llm-image .

3. Run the Docker container.

       docker run -p 11434:11434 llm-image

Guidelines for contributing to the project, including coding standards, pull request process, etc.

Information about the project's license.

How to get in touch with the project team.