This project provides an AI-powered tool to automatically generate comprehensive Markdown README files and interactive wikis for any software repository. It targets developers and project maintainers seeking to streamline documentation creation, offering context-aware content generation, automatic badge embedding, and smart logo design.

How It Works

The tool leverages large language models (LLMs) and text-to-image models to analyze project structure, identify technologies, and generate descriptive content. It supports Retrieval-Augmented Generation (RAG) for enhanced context awareness and can be configured to use local or remote AI models and API endpoints. This approach allows for tailored documentation that accurately reflects the project's specifics.

Quick Start & Requirements

• Install via pip: pip install readmex
• Requires Python 3.7+.
• API keys for LLM and Text-to-Image models are mandatory. Configuration can be done via environment variables (LLM_API_KEY, T2I_API_KEY) or a global config file (~/.readmex/config.json).
• Optional configuration for embedding models and performance tuning is available.
• See Docs for detailed setup.

Highlighted Details

• Supports a wide range of programming languages and web technologies for tech stack identification.
• Offers command-line options for interactive generation, website creation (MkDocs), deployment, and debugging.
• Can generate project structure files, script descriptions, and requirements.txt.
• Includes features for auto-generating badges and a project logo.

Maintenance & Community

• The project is actively maintained by aibox22.
• A QQ group is available for discussion and support: 2161023585.

Licensing & Compatibility

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

Limitations & Caveats

The project is still under development, with features like prompt engineering for logo generation and multi-language support listed on the roadmap. Some AI model configurations might require specific API endpoints or local model setups.