Autodiff Python Packages

uncertainties

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

2.7M 667 85

autograd-gamma

NotImplementedError: VJP of gammainc wrt argnum 0 not defined

1.9M 15 4

pennylane-catalyst

A JIT compiler for hybrid quantum programs in PennyLane

15K 211 73

hyperjet

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

4K 17 4

gradgen

Autodiff from Python to Embedded Rust

4K 8 0

trace-opt

End-to-end Generative Optimization for AI Agents

3K 735 57

nufftax

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

2K 16 1

mygrad

Drop-in autodiff for NumPy.

1K 216 23

kineverse

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

1K 3 0

dlux

Differentiable Physical Optics Propagation in Jax

1K 71 17

hypergraph

Reversed mode second order automatic differentiation for python (WIP)

1K 4 0

optyx

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

975 25 2

nabla-ml

Nabla: High-Performance Scientific Computing

863 336 13

betty-ml

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

706 348 29

autobound

AutoBound automatically computes upper and lower bounds on functions.

556 365 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!

418 10 1

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.

360 0 0