This Python script automates the analysis of GitHub repositories for Large Language Models (LLMs), extracting READMEs, repository structure, and non-binary file contents. It provides structured outputs with pre-formatted prompts to aid in comprehensive repo evaluation, targeting developers and researchers working with LLMs.

How It Works

The script uses an iterative traversal method to map repository structure, avoiding recursion limits. It selectively extracts text content from files, intelligently skipping binary files to ensure efficient processing and focus on analyzable data.

Quick Start & Requirements

• Install: pip install PyGithub tqdm
• Prerequisites: Python, GitHub Personal Access Token (as GITHUB_TOKEN environment variable).
• Usage: Run python repototxt.py and enter the repository URL.

Highlighted Details

• README retrieval for initial insights.
• Structured repository traversal without recursion limits.
• Selective extraction of text file contents, skipping binaries.
• Outputs include analysis prompts for LLM guidance.

Maintenance & Community

Contributions are welcomed via pull requests and issue reporting.

Licensing & Compatibility

Licensed under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

Requires a GitHub Personal Access Token for operation. The script's effectiveness is dependent on the quality and format of the repository's files.