This Python script converts GitHub repositories into single files, ideal for feeding codebases into large-context AI models. It supports public and private repos, language filtering, and optional comment removal, streamlining code sharing for AI-assisted development and analysis.

How It Works

The script clones a specified GitHub repository, optionally filters files by language or excludes directories/types, and then concatenates the content of the selected files into a single output file. For Python files, it can optionally strip comments and docstrings to reduce token count. A separate script handles TypeScript, JavaScript, Svelte, and Rust.

Quick Start & Requirements

• Install via Conda: conda create -n g2f python=3.10 && conda activate g2f && pip install -r requirements.txt
• Requires Python 3.x and the requests library.
• Official documentation and GUI available at github2file-tkinter-GUI.py.

Highlighted Details

• Supports public and private GitHub repositories.
• Filters files by language (Python, Markdown, Go, JavaScript) and allows directory/file type exclusion.
• Optional removal of comments and docstrings from Python code.
• Includes a separate script (ts-js-rust2file.py) for TypeScript, JavaScript, Svelte, and Rust.
• Offers a GUI interface (github2file-tkinter-GUI.py) for easier usage.
• Includes a --claude option for specific output formatting.

Maintenance & Community

No specific contributors, sponsorships, or community links (Discord/Slack) are mentioned in the README.

Licensing & Compatibility

• MIT License.
• Permissive license suitable for commercial use and integration with closed-source projects.

Limitations & Caveats

The script's effectiveness relies on the AI model's ability to interpret the concatenated code. The README does not detail specific error handling for large repositories or complex project structures.