jrjModelRegistry is a lightweight and flexible Python library for saving, versioning, and serving machine learning models.
- π¦ Store models in S3-compatible storage with ZIP encryption
- ποΈ Track metadata in MongoDB
- β‘ Dynamically serve models using built-in FastAPI routes and dashboard
- β Works with any Python object (models, transformers, even DataFrames)
Simple enough for small projects, powerful enough for production.
π Read the Docs π¦ View on PyPI β Star on GitHub
Looking for usage examples, API details, and setup guides?
π Full documentation is available here: https://jrjmodelregistry.super.site