google/magika
🔧 Toolgoogle
AI tool that detects file types by content, not extension.
Magika employs a deep neural network to classify file content, achieving high accuracy even for ambiguous or unknown files. The model is trained on millions of files and can distinguish between similar formats (e.g., different document or image types). It provides a command-line interface and a Python API for batch processing. The ONNX runtime ensures low-latency inference suitable for production environments.
💡Highlights
- ├─100+ file types supported
- ├─Deep learning based classification
- └─Fast ONNX inference
🎯For
- ├─Developers
- ├─Security Researchers
- └─Data Scientists