Pde Python Packages

scikit-fem

Simple finite element assemblers

findiff

Python package for numerical derivatives and partial differential equations in any number of dimensions.

exponax

Efficient Differentiable n-d PDE Solvers in JAX.

pdequinox

Neural Emulator Architectures in JAX.

trainax

Neural Emulator Architectures in JAX.

apebench

[Neurips 2024] A benchmark suite for autoregressive neural emulation of PDEs. (≥46 PDEs in 1D, 2D, 3D; Differentiable Physics; Unrolled Training; Rollout Metrics)

scientific-computing-system-2-0

Scientific computing platform on NumPy/SciPy/pandas/matplotlib: linear algebra, stats, optimization, signals, ML, information theory, chaos, Bayes, metaheuristics, geometry and RL.

devsim

TCAD Semiconductor Device Simulator

deepxde

A library for scientific machine learning and physics-informed learning

felupe

Open finite element infrastructure for nonlinear computational mechanics.

axiomize

Reproducible scientific modeling engine and agent skill pack: versioned Model IR with mandatory units, dimensional and numerical validation, calibration, uncertainty analysis, and portable export (SBML, CellML, Modelica) via CLI, REST and MCP. Install: pip install axiomize.

mathematicskit

See how the algorithms of computational mathematics work: a Python toolkit for learning and teaching numerical methods, dynamical systems, and discrete math across 18 domains, built on numpy/scipy

physai

PhysAI is an open-source, multi-backend framework for solving partial differential equations with Physics-Informed Neural Networks (PINNs), Fourier Neural Operators (FNOs), and Unified Spectral Element architectures. Has 57 pre-configured residuals and a built-in packaged numerical solver for most geometries and equations.

sympde

Symbolic calculus for partial differential equations (and variational forms)

semiflow-pde

Fast no_std Rust library for evolution equations and PDEs via Chernoff approximation of operator semigroups — heat, Schrödinger, diffusion, graph & manifold operators. Bindings for C, Python, and WebAssembly.

opinf

Operator Inference for data-driven, non-intrusive model reduction of dynamical systems.

mgfd

Meshless Generalized Finite Differences (mGFD) solver and reference point-cloud datasets for 2D PDEs on irregular domains, with reproducible batches and benchmarks.

jaxdf

A JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations

tensormesh-fem

A fast, differentiable, JIT-free, debugging-friendly finite element library for PyTorch.

flashslice

Fused Triton kernels for Transolver's slice/deslice. Official code for "Does Transolver really need a Transformer?" (arXiv:2609.32525)

pyfvm

Finite volume discretization tools for Python.

phaethon

End-to-End Physics-Constrained Scientific Computing & Sci-ML Framework

rom-operator-inference

Operator Inference for data-driven, non-intrusive model reduction of dynamical systems.

pyro-hydro

A framework for hydrodynamics explorations and prototyping