Autodiff Python Packages

uncertainties

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

2.9M 671 86

autograd-gamma

NotImplementedError: VJP of gammainc wrt argnum 0 not defined

1.7M 15 4

pennylane-catalyst

A JIT compiler for hybrid quantum programs in PennyLane

19K 218 79

hyperjet

Algorithmic differentiation with hyper-dual numbers in C++ and Python

4K 17 4

nufftax

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

3K 28 2

dlux

Differentiable Physical Optics Propagation in Jax

2K 73 17

betty-ml

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

1K 347 28

trace-opt

End-to-end Generative Optimization for AI Agents

1K 745 59

mygrad

Drop-in autodiff for NumPy.

1K 217 23

hypergraph

Reversed mode second order automatic differentiation for python

1K 4 0

nabla-ml

Nabla: High-Performance Scientific Computing

1K 341 13

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.

916 0 0

gradgen

Autodiff from Python to Embedded Rust

907 8 0

optyx

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

854 25 3

kineverse

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

757 3 0

autobound

AutoBound automatically computes upper and lower bounds on functions.

500 365 19

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!

454 10 1