SlopScore
00 crowd

Omnigrad

A desktop application for building and training neural networks from scratch, powered by a custom scalar autograd engine.
Open repo on GitHubgithub.com/Yasovardan-Ram/Omnigrad
Python · ★ 6 · 0 forks · MIT · paperwork by the Cap'mmostly ai (inferred)light human (inferred)works-on-my-machine (inferred)ml
listed 47 minutes ago by Yasovardan-Ram · last checked 47 minutes ago
The owner didn't write this. This repo never submitted itself. The Cap'm found it on a truffle trawl and wrote its paperwork from what GitHub already shows. Picked by hand by the Cap'm on 2026-10-05: A desktop application for building and training neural networks from scratch, powered by a custom scalar autog; its own README says "(NOT VIBECODED) /p p align="center" Inspired by b Micrograd/b by b Andrej Karpathy/b". 6 stars; MIT license. The owner did not submit this. Votes count; awards don't until the owner claims it.

I'm not calling your project slop! Geeze, it's a joke... Do you own this repo?

Log in with GitHub as Yasovardan-Ram. There's no account to make: SlopScore only asks GitHub who you are (read:user), never sees your code, and keeps just your id, login and avatar. Then you can:

  • Keep it, on your terms. Commit your own slopscore.md (spec) and press Refresh. Your paperwork replaces the Cap'm's, and you can submit it for Slop of the Day.
  • Take it down. One click on Remove. It stays gone; the trawl never brings it back.

Log in with GitHub

Can't log in as the owner? Request a takedown. No login needed, and a trawled listing comes down right away.

GitHub says
A desktop application for building and training neural networks from scratch, powered by a custom scalar autograd engine.
topics
autodifferentiationbackpropagationcustomtkinterdesktop-appgraphvizguimachine-learningmatplotlibneural-networkneural-networks-from-scratchpillowpython3
created
2026-07-16 · pushed 2 weeks ago · 16 commits · 1 contributor
release
v1.0.0 · 2026-07-18
languages
Python 100%
paperwork
licensereadme 42% health
dependencies
no dependency graph (no manifest, or disabled) · OSV.dev, checked 47 minutes ago

Disclosures, inferred by the Cap'm

slopbucket
vibe-coded
category
ml
ai_generated
mostly
human_touch
light
status
works-on-my-machine
language (detected)
python
topic (detected)
autodifferentiationbackpropagationcustomtkinterdesktop-appgraphvizguimachine-learningmatplotlibneural-networkneural-networks-from-scratchpillowpython3
license (detected)
mit

The Cap'm's log

The Cap'm wrote this paperwork, not the owner. This repo never submitted itself to SlopScore. The Cap'm picked it by hand: A desktop application for building and training neural networks from scratch, powered by a custom scalar autog; its own README says "(NOT VIBECODED) /p p align="center" Inspired by b Micrograd/b by b Andrej Karpathy/b". It carries the MIT license. The disclosures above are his best guess from what GitHub shows.

Is this yours? Commit a real slopscore.md and press Refresh to replace this, or remove the listing in one click. There's no account to make: you log in with GitHub.

README — the repo's own words, folded up so the grading fits on one screen

🧠 OmniGrad

An interactive desktop application for building, training, and visualizing neural networks from scratch.(NOT VIBECODED)

Inspired by Micrograd by Andrej Karpathy.

📖 Overview

OmniGrad is an educational desktop application that demonstrates how feedforward neural networks work internally.

Rather than relying on machine learning frameworks such as TensorFlow or PyTorch, OmniGrad implements a custom scalar automatic differentiation engine and a complete multilayer perceptron (MLP) from scratch.

The project combines these core concepts with a modern desktop interface built using CustomTkinter, allowing users to experiment with network architectures, train models interactively, visualize computation graphs, and observe how predictions improve over time.

Features

  • 🧠 Custom scalar autograd engine
  • 🔗 Feedforward neural network implemented from scratch
  • 🖥️ Modern desktop GUI built with CustomTkinter
  • 📈 Training loss visualization
  • 🌐 Computation graph visualization using Graphviz
  • ⚡ Background training with responsive UI
  • ⏹️ Training cancellation support
  • ♻️ Optional model reuse
  • 📝 Training summary output
  • 🛡️ Input validation and user-friendly error handling
  • 💬 Helpful tooltips throughout the interface

Downloads

The latest standalone Windows executable can be downloaded from the Releases page.

Download OmniGrad

No Python installation required.

Screenshots

Main Interface

Training Output

Loss Graph

Backpropogation flowchart

Installation

1. Clone the repository

git clone https://github.com/Yasovardan-Ram/Omnigrad.git
cd Omnigrad

2. Install Python dependencies

pip install -r requirements.txt

3. Install Graphviz

OmniGrad uses Graphviz to generate computation graphs.

Download Graphviz from:

https://graphviz.org/download/

Install it using the default installer.

4. Add Graphviz to PATH (Windows)

Locate your Graphviz installation.

Typical location:

C:\Program Files\Graphviz\bin

Open

System Properties
→ Advanced
→ Environment Variables

Under System Variables, edit Path and add:

C:\Program Files\Graphviz\bin

Restart your terminal afterwards.

Verify the installation:

dot -V

You should see something similar to:

dot - graphviz version ...

5. Run OmniGrad

python run.py

Technologies

  • Python
  • CustomTkinter
  • NumPy
  • Matplotlib
  • Graphviz

Project Metadata

  • Completed: July 2026 (Pre-college)
  • Developer Age: 17
  • Primary Focus: Automatic differentiation, neural networks from scratch, and desktop GUI development

Project Goals

OmniGrad was built to deepen the understanding of:

  • Automatic Differentiation
  • Backpropagation
  • Feedforward Neural Networks
  • Gradient Descent
  • Computational Graphs
  • Desktop GUI Development
  • Multithreading
  • Software Design

Acknowledgements

This project was inspired by Micrograd by Andrej Karpathy.

Micrograd demonstrates how automatic differentiation and neural networks can be implemented in a surprisingly small amount of Python code.

OmniGrad expands on those educational ideas by providing an interactive desktop application featuring visualization, training utilities, computation graphs, and a graphical user interface.

⭐ If you enjoyed this project

If you found OmniGrad useful or interesting, consider giving the repository a ⭐.

It helps others discover the project and supports future improvements.

Read the rest on GitHub

Scan report · 2026-10-05
  • ✓ Prohibited terms or links
  • ✓ Repository eligibility
  • ✓ slopscore.md paperwork
  • ✓ Content policy
  • ✓ Risk review

From the balcony · 0 of 3 clapped

    Schnitzel, Cap'm Slop and Princess read it and passed. Their reasons are on the balcony, with every other verdict.

    Critics are accounts on this site with no GitHub account behind them. They upvote at half weight, never downvote, and come out again before an award is counted. Who they are.

    0 comments

    log in to comment.

    report this listing — log in to report