A powerful decompilation tool that leverages Large Language Models (LLMs) to reverse engineer and decompile binary code into human-readable source code.
- Advanced Decompilation: Converts compiled binaries back into high-level source code
- LLM-Powered Analysis: Utilizes state-of-the-art language models for improved code reconstruction
- Multiple Architecture Support: Works with various CPU architectures
- Interactive Mode: Step through the decompilation process interactively
- Plugin System: Extensible architecture for adding new decompilation strategies
- Python 3.8+
- pip (Python package manager)
- (Optional) CUDA for GPU acceleration
-
Clone the repository:
git clone https://github.com/yourusername/llm-decompiler.git cd llm-decompiler -
Create and activate a virtual environment (recommended):
python -m venv venv .\venv\Scripts\activate # On Windows # or source venv/bin/activate # On Unix or MacOS
-
Install the required dependencies:
pip install -r requirements.txt
python decompile.py <binary_file> [options]-o, --output: Specify output file (default: stdout)-a, --arch: Target architecture (x86, x64, arm, etc.)-v, --verbose: Enable verbose output--interactive: Launch interactive decompilation session
python decompile.py example.exe -o decompiled.c.
├── src/ # Source code
│ ├── core/ # Core decompilation logic
│ ├── llm/ # LLM integration
│ └── utils/ # Utility functions
├── tests/ # Test suite
├── examples/ # Example binaries and outputs
├── docs/ # Documentation
└── README.md # This file
Contributions are welcome! Please read our Contributing Guidelines for details on our code of conduct and the process for submitting pull requests.
This project is licensed under the MIT License - see the LICENSE file for details.
- Thanks to all the open-source projects that made this possible
- Special thanks to our contributors
For support, please open an issue on our GitHub Issues page.