Autodiff Python Packages

uncertainties

Transparent calculations with uncertainties on the quantities involved (aka "error propagation"); calculation of derivatives.

2.1M 665 85

autograd-gamma

NotImplementedError: VJP of gammainc wrt argnum 0 not defined

2M 15 4

pennylane-catalyst

A JIT compiler for hybrid quantum programs in PennyLane

12K 208 71

hyperjet

Automatic differentiation with dual numbers

5K 17 4

gradgen

Autodiff from Python to Embedded Rust

4K 7 0

trace-opt

End-to-end Generative Optimization for AI Agents

3K 730 58

kineverse

Version 2.0 of Kineverse, a framework for modeling kinematics for robotic manipulation and control.

2K 3 0

dlux

Differentiable Optical Models as Parameterised Neural Networks in Jax using Zodiax.

1K 71 16

hypergraph

Reversed mode second order automatic differentiation for python (WIP)

1K 4 0

mygrad

Drop-in automatic differentiation to NumPy

1K 216 22

nabla-ml

Nabla: High-Performance Scientific Computing

1K 335 13

optyx

Intuitive symbolic interface for constrained optimization problems. Write natural Python, get automatic gradients and solvers.

753 25 2

betty-ml

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization

553 348 29

ym-pure-ml

Transparent, NumPy-only deep learning framework for teaching, small-scale projects, prototyping, and reproducible experiments. No CUDA, no giant dependency tree. Batteries included: VJP autograd, layers, activations, losses, optimizers, Zarr checkpoints, and more!

543 10 1

smallpebble

A minimalist deep learning library written from scratch in Python

448 133 13

autobound

AutoBound automatically computes upper and lower bounds on functions.

438 365 19

nufftax

Pure JAX implementation of the Non-Uniform Fast Fourier Transform (NUFFT)

406 13 1

mrphy

A Pytorch based tool for MR physics simulations

298 5 3

co2-eos

Differentiable CO₂ thermodynamic properties in JAX. Pure-JAX Span-Wagner equation of state — JIT-compiled, vmappable, and fully differentiable via jax.grad. Phase-aware solvers robust through the critical point. Allows GPU speedup over CoolProp for CO₂.

216 0 0