Geometric Deep Learning Python Packages

torch-geometric

Graph Neural Network Library for PyTorch

openequivariance

OpenEquivariance: a fast, open-source GPU JIT kernel generator for the Clebsch-Gordon Tensor Product.

pyg-nightly

Graph Neural Network Library for PyTorch

torch-cluster

PyTorch Extension Library of Optimized Graph Cluster Algorithms

abstractintegratedmodule

[~] IntegratedPipeline is a standalone AI Agent Library for Non-LLM memory Augmented Agentic Framework, Specifically designed to provide Agentic capability for any Autonomous Agentic Framework locally and Coordinatively that runs efficiently on Consumer based machine to High end embedded systems, While continuously learning and runs efficiently.

dgllife

Python package for graph neural networks in chemistry and biology

pypose

A library for differentiable robotics on manifolds.

torch-spline-conv

Implementation of the Spline-Based Convolution Operator of SplineCNN in PyTorch

sphericart-torch

Multi-language library for the calculation of spherical harmonics in Cartesian coordinates

escnn

Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/

sphericart

Multi-language library for the calculation of spherical harmonics in Cartesian coordinates

graphein

Protein Graph Library

sphericart-jax

Multi-language library for the calculation of spherical harmonics in Cartesian coordinates

neuralogic

PyNeuraLogic lets you use Python to create Differentiable Logic Programs

vn-transformer

A Transformer made of Rotation-equivariant Attention using Vector Neurons

stellargraph

StellarGraph - Machine Learning on Graphs

graphgallery

GraphGallery is a gallery for benchmarking Graph Neural Networks

avitai-artifex

A research-focused modular generative modeling library built on JAX/Flax NNX

aidsorb

Python package for deep learning on porous materials and beyond.

topogeoml

Preregistered topology-aware machine learning research toolkit: differentiable persistent homology, Hodge Laplacian message passing, and statistically defensible benchmarking on graph classification (MUTAG, PROTEINS, NCI1).

pytorch-hexagdly

Process hexagonally sampled data with PyTorch

openequivariance-extjax

OpenEquivariance: a fast, open-source GPU JIT kernel generator for the Clebsch-Gordon Tensor Product.

cellshape

3D shape analysis using deep learning

groupoid

Pre-alpha groupoid/sheaf/Riemannian aggregation prototype for federated learning; tested math components, not production FL.