DevPal - AI CLI Tool for Developers

🧠 DevPal is an intelligent command-line assistant that helps developers understand, refactor, document, and test codebases using Retrieval-Augmented Generation (RAG) and Large Language Models.

✨ Features

🔍 Code Understanding

• Semantic Search: Ask questions about your codebase using natural language
• Error Explanation: Get detailed explanations of error messages and stack traces
• Code Analysis: Understand complex functions and their relationships

🛠️ Development Tools

• Unit Test Generation: Automatically generate tests for your functions
• Code Refactoring: Get AI-powered suggestions for code improvements
• Documentation: Auto-generate docstrings and documentation

🎯 Interactive Experience

• CLI Interface: Fast, efficient command-line operations
• TUI Mode: Optional Textual-based user interface for interactive exploration
• Project Initialization: One-command setup for new projects

🚀 Quick Start

Installation

1. Clone the repository

   git clone <repository-url>
   cd devpal

2. Set up virtual environment

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies

   pip install -r requirements.txt

4. Configure environment

   cp .env.example .env
   # Edit .env with your API keys

Basic Usage

1. Initialize a project

   devpal init /path/to/your/project

2. Ask questions about your code

   devpal ask "What does the main function do?"

3. Generate tests

   devpal test src/main.py

4. Get error explanations

   devpal explain "TypeError: 'int' object is not callable"

5. Refactor code

   devpal patch src/main.py --function process_data

6. Generate documentation

   devpal docs src/main.py

7. Launch interactive TUI

   devpal tui

📋 Commands

devpal init <project_path>

Walks through the project directory, extracts code, and builds a ChromaDB vector store for semantic search.

Options:

• --skip-dirs: Comma-separated list of directories to skip
• --file-types: Comma-separated list of file extensions to include

devpal ask <question>

Performs semantic search over your codebase and answers questions using RAG.

Options:

• --file: Limit search to specific file
• --function: Limit search to specific function
• --model: Choose LLM model (gemini, claude, deepseek, openai, ollama, huggingface)

devpal explain <error_message>

Analyzes error messages and provides detailed explanations with potential solutions.

devpal test <file_path>

Generates unit tests for functions in the specified file.

Options:

• --function: Generate tests for specific function only
• --framework: Test framework (pytest, unittest, jest)
• --output: Output file path

devpal patch <file_path>

Suggests improvements and refactoring for code in the specified file.

Options:

• --function: Refactor specific function only
• --dry-run: Show changes without applying them
• --backup: Create backup before applying changes

devpal docs <file_path>

Generates documentation for the specified file.

Options:

• --format: Output format (markdown, jsdoc, python)
• --output: Output file path

devpal tui

Launches an interactive Textual-based user interface for exploring your codebase.

🔧 Configuration

Create a .env file in your project root:

# LLM Configuration
GOOGLE_API_KEY=your_gemini_api_key
CLAUDE_API_KEY=your_claude_api_key
DEEPSEEK_API_KEY=your_deepseek_api_key
OPENAI_API_KEY=your_openai_api_key
HUGGINGFACE_API_KEY=your_huggingface_api_key

# Model Settings
DEFAULT_MODEL=claude
EMBEDDING_MODEL=all-MiniLM-L6-v2

# ChromaDB Settings
CHROMA_PERSIST_DIRECTORY=./chroma_store

# Development Settings
DEBUG=false
LOG_LEVEL=INFO

🏗️ Architecture

devpal/
├── src/
│   ├── core/           # Core functionality
│   ├── cli/            # CLI commands
│   ├── tui/            # Textual UI components
│   ├── models/         # LLM and embedding models
│   ├── vectorstore/    # ChromaDB integration
│   └── utils/          # Utility functions
├── tests/              # Test suite
├── examples/           # Example projects
└── docs/              # Documentation

🧪 Testing

Run the test suite:

pytest tests/

Run with coverage:

pytest --cov=src tests/

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests for new functionality
5. Submit a pull request

📄 License

MIT License - see LICENSE file for details.

🆘 Support

• Issues: Report bugs and feature requests on GitHub
• Discussions: Join community discussions
• Documentation: Check the docs folder for detailed guides
• LLM Guide: See LLM_GUIDE.md for detailed LLM configuration and usage

---

DevPal - Making code understanding and development easier with AI! 🚀