Physics Informed Machine Learning Python Packages

agentfem

AI-native open-source finite-element platform connecting engineering, computation, data, and AI.

carnopy

Reproducible thermophysical datasets from scientific backends with visualization, provenance, and leakage-aware preparation for physics-informed machine-learning and engineering workflows.

matgpr

Gaussian Process Regression toolkit for materials informatics, including physics-informed mean functions.

separable-operator-networks

Official repo for separable operator networks -- extreme-scale operator learning for parametric PDEs.

mechanicsdsl-datasets

Reference datasets for physics parameter estimation and inverse problem benchmarking. Synthetic data with ground truth, experimental trajectories, and paired MCMC posteriors.