folder2md4llms 0.4.28

Enhanced tool to concatenate folder contents into markdown format for LLM consumption

folder2md4llms

folder2md4llms is a powerful and flexible tool that converts a repository's contents into a single, LLM-friendly Markdown file. It's designed to be fast, configurable, and easy to use, with a focus on producing high-quality, structured output.

✨ Key Features

• Smart Condensing: Automatically condenses code to fit within a specified token or character limit without crude truncation.
• Document Conversion: Converts PDF, DOCX, XLSX, and other document formats into text.
• Binary File Analysis: Provides intelligent descriptions for images, archives, and other binary files.
• Highly Configurable: Use a folder2md.yaml file or command-line options to customize the output.
• Fast and Efficient: Leverages multi-threading and efficient file processing to handle large repositories quickly.
• Advanced Filtering: Uses .gitignore-style patterns to exclude files and directories.

🚀 Quick Start

Installation

# Using uv (recommended)
uv add folder2md4llms

# Using pip
pip install folder2md4llms

Basic Usage

# Process the current directory and save to output.md
folder2md .

# Process a specific directory and set a token limit
folder2md /path/to/repo --limit 80000t

# Copy the output to the clipboard
folder2md /path/to/repo --clipboard

# Generate a .folder2md_ignore file
folder2md --init-ignore

For a full list of commands and options, see the CLI Reference or run folder2md --help.

🔧 Configuration

You can configure folder2md4llms by creating a folder2md.yaml file in your repository's root directory. This allows you to set advanced options and define custom behavior.

For more details, see the Configuration Guide.

🛠️ Development

Interested in contributing? Get started with these simple steps:

# Clone the repository
git clone https://github.com/henriqueslab/folder2md4llms.git
cd folder2md4llms

# Set up the development environment
make setup

# See all available commands
make help

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For more information, see the Contributing Guidelines.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.