I built a tool to turn any GitHub repo into a single text prompt for any AI.

Introducing CopyGit: Streamlining AI Data Preparation from GitHub Repositories

In the rapidly evolving landscape of artificial intelligence, efficiently integrating code and documentation from repositories into AI workflows remains a significant challenge. Manually copying and pasting multiple files into large language models (LLMs) can be tedious and time-consuming. Addressing this pain point, a new tool named CopyGit has been developed to simplify this process and enhance productivity.

What is CopyGit?

CopyGit is a streamlined web application designed to convert any GitHub repository into a single, structured text prompt suitable for use with AI models. By simply providing a GitHub URL, users can quickly generate a comprehensive, organized text bundle that encapsulates the repository’s contents, including a clear directory hierarchy.

How Does It Work?

Using CopyGit is intuitive:
1. Paste the URL of the desired GitHub repository into the tool.
2. Select the specific files or folders you want to include.
3. Generate a structured text output that presents the selected files along with a directory tree outline.

This resulting text bundle can then be directly pasted into an AI prompt, facilitating seamless integration of repository data into AI workflows.

Key Features

• Support for Private Repositories: Users can retrieve content from private GitHub repositories by enabling token authentication. Importantly, tokens are stored locally within your browser for security, not transmitted externally.

• Token Usage Monitoring: An integrated token counter informs users of the amount of data being processed, helping avoid exceeding language model context limits.

• Content Filtering: To reduce noise and unnecessary data, CopyGit automatically filters out boilerplate code such as images, binaries, and lockfiles, focusing on meaningful source code and documentation.

Open Source and Free

CopyGit is an open-source project, fostering community collaboration and transparency. It is freely accessible to all interested users.

• Try it live: https://copygit.vercel.app
• View the source code: https://github.com/XeCipher/CopyGit

Conclusion

CopyGit aims to enhance the efficiency of AI developers and data scientists by simplifying the process of incorporating GitHub repository content into AI models. Its user-friendly interface, support for private repositories, and thoughtful features make it a valuable tool for those looking to streamline their AI workflows.

We welcome feedback and suggestions to further improve this open-source project. Feel free to explore and contribute!