kan
One library, four surfaces. Production-grade Kolmogorov-Arnold Networks || TensorFlow + PyTorch + ONNX. || A small KAN beats a 10× larger MLP on smooth, separable target. One library. Two backends. Real ONNX export. Docker + Kubernetes ready.
Parametric differentiable curves with PyTorch for continuous embeddings, shape-restricted models, or KANs
ikan: many kan variants for every body
PyTorch implementation of QKAN "Quantum-inspired Kolmogorov-Arnold Network" https://arxiv.org/abs/2509.14026
LinearKAN: A very fast implementation of Kolmogorov-Arnold Networks
