phydra-labs/phydrax
Modular Physics-ML Components in JAX
This tool helps scientists and engineers working with Partial Differential Equations (PDEs) to build and train physics-informed machine learning models. You define a physical domain, input data (like boundary conditions or observed measurements), and then define the governing physics equations. The tool outputs a trained model that satisfies both your data and the physical laws you've specified, allowing you to simulate or predict complex physical phenomena.
Use this if you need to solve complex physical problems by blending data-driven machine learning with fundamental physics equations, especially for systems modeled by Partial Differential Equations.
Not ideal if your primary goal is to perform general-purpose data analysis, standard supervised machine learning, or if you require a tool for commercial production use without a separate license.
Stars
11
Forks
—
Language
Python
License
—
Category
Last pushed
Feb 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/phydra-labs/phydrax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/