MyTorch – Minimalist autograd in 450 lines of Python (github.com)

HmcKk

Karpathy’s micrograd did it first (and better); start here: https://karpathy.ai/zero-to-hero.html

Better readme would be way to go

Having written a slightly more involved version of this recently myself I think you did a great job of keeping this compact while still readable. This style of library requires some design for sure.

Supporting higher order derivatives was also something I considered, but it’s basically never needed in production models from what I’ve seen.