AI-Powered Repository Documentation Generation • Multi-Language Support • Architecture-Aware Analysis

Generate holistic, structured documentation for large-scale codebases • Cross-module interactions • Visual artifacts and diagrams

Quick Start • CLI Commands • Output Structure • Paper

# Install from source pip install git+https://github.com/FSoft-AI4Code/CodeWiki.git # Verify installation codewiki --version

CodeWiki supports multiple models via an OpenAI-compatible SDK layer.

codewiki config set \ --api-key YOUR_API_KEY \ --base-url https://api.anthropic.com \ --main-model claude-sonnet-4 \ --cluster-model claude-sonnet-4

# Navigate to your projectcd /path/to/your/project # Generate documentation codewiki generate # Generate with HTML viewer for GitHub Pages codewiki generate --github-pages --create-branch

That's it! Your documentation will be generated in ./docs/ with comprehensive repository-level analysis.

CodeWiki is an open-source framework for automated repository-level documentation across seven programming languages. It generates holistic, architecture-aware documentation that captures not only individual functions but also their cross-file, cross-module, and system-level interactions.

🐍 Python • ☕ Java • 🟨 JavaScript • 🔷 TypeScript • ⚙️ C • 🔧 C++ • 🪟 C#

# Set up your API configuration codewiki config set \ --api-key <your-api-key> \ --base-url <provider-url> \ --main-model <model-name> \ --cluster-model <model-name># Show current configuration codewiki config show # Validate your configuration codewiki config validate

# Basic generation codewiki generate # Custom output directory codewiki generate --output ./documentation # Create git branch for documentation codewiki generate --create-branch # Generate HTML viewer for GitHub Pages codewiki generate --github-pages # Enable verbose logging codewiki generate --verbose # Full-featured generation codewiki generate --create-branch --github-pages --verbose

• API keys: Securely stored in system keychain (macOS Keychain, Windows Credential Manager, Linux Secret Service)
• Settings: ~/.codewiki/config.json

Generated documentation includes both textual descriptions and visual artifacts for comprehensive understanding.

• Repository overview with architecture guide
• Module-level documentation with API references
• Usage examples and implementation patterns
• Cross-module interaction analysis

• System architecture diagrams (Mermaid)
• Data flow visualizations
• Dependency graphs and module relationships
• Sequence diagrams for complex interactions

./docs/ ├── overview.md # Repository overview (start here!) ├── module1.md # Module documentation ├── module2.md # Additional modules... ├── module_tree.json # Hierarchical module structure ├── first_module_tree.json # Initial clustering result ├── metadata.json # Generation metadata └── index.html # Interactive viewer (with --github-pages) 

CodeWiki has been evaluated on CodeWikiBench, the first benchmark specifically designed for repository-level documentation quality assessment.

View comprehensive results: See paper for complete evaluation on 21 repositories spanning all supported languages.

CodeWiki employs a three-stage process for comprehensive documentation generation:

1. Hierarchical Decomposition: Uses dynamic programming-inspired algorithms to partition repositories into coherent modules while preserving architectural context across multiple granularity levels.

2. Recursive Multi-Agent Processing: Implements adaptive multi-agent processing with dynamic task delegation, allowing the system to handle complex modules at scale while maintaining quality.

3. Multi-Modal Synthesis: Integrates textual descriptions with visual artifacts including architecture diagrams, data-flow representations, and sequence diagrams for comprehensive understanding.

┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐ │ Codebase │───▶│ Hierarchical │───▶│ Multi-Agent │ │ Analysis │ │ Decomposition │ │ Processing │ └─────────────────┘ └──────────────────┘ └─────────────────┘ │ │ ▼ ▼ ┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐ │ Visual │◀───│ Multi-Modal │◀───│ Structured │ │ Artifacts │ │ Synthesis │ │ Content │ └─────────────────┘ └──────────────────┘ └─────────────────┘ 

• Python 3.12+
• Node.js (for Mermaid diagram validation)
• LLM API access (Anthropic Claude, OpenAI, etc.)
• Git (for branch creation features)

• Docker Deployment - Containerized deployment instructions
• Development Guide - Project structure, architecture, and contributing guidelines
• CodeWikiBench - Repository-level documentation benchmark
• Live Demo - Interactive demo and examples

• Paper - Full research paper with detailed methodology and results
• Citation - How to cite CodeWiki in your research

If you use CodeWiki in your research, please cite:

@misc{hoang2025codewikievaluatingaisability, title={CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases}, author={Anh Nguyen Hoang and Minh Le-Anh and Bach Le and Nghi D. Q. Bui}, year={2025}, eprint={2510.24428}, archivePrefix={arXiv}, primaryClass={cs.SE}, url={https://arxiv.org/abs/2510.24428}, }

This project is licensed under the MIT License.