Habrador/MicrogradCSharp
The easiest way to build Neural Networks in C# within Unity. The open-source AI project implements a scalar-valued autograd engine so you don't have to deal with backpropagation, and a Neural Network library. You can use it outside of Unity as well.
This project helps C# developers build and train neural networks for various AI tasks directly within the Unity game engine or other C# applications. You input your raw data and the desired network architecture, and it outputs a trained neural network capable of making predictions or classifications. Game developers and AI researchers who use C# will find this useful for prototyping and implementing AI behaviors.
No commits in the last 6 months.
Use this if you are a C# developer or Unity game developer who wants to implement machine learning models like regression, classification, or even reinforcement learning without manually coding complex backpropagation algorithms.
Not ideal if you are not a C# developer or if you require a pre-built, high-level machine learning framework with extensive data science toolkits.
Stars
10
Forks
2
Language
C#
License
MIT
Category
Last pushed
Oct 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Habrador/MicrogradCSharp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JonathanRaiman/theano_lstm
:microscope: Nano size Theano LSTM module
google/tangent
Source-to-Source Debuggable Derivatives in Pure Python
ahrefs/ocannl
OCANNL: OCaml Compiles Algorithms for Neural Networks Learning
yoshoku/numo-openblas
Numo::OpenBLAS builds and uses OpenBLAS as a background library for Numo::Linalg
statusfailed/catgrad
a categorical deep learning compiler