Analysis updated 2026-05-18
Work through 30 interactive lessons to learn how neural networks and large language models work.
Play with browser demos like dragging neuron weights or exploring word vectors in 3D.
Learn to call a real AI API and build a small knowledge base by the end of the course.
| buynao/aipath | kappaemme-git/local-client-prospector-skill | sveltejs/esrap | |
|---|---|---|---|
| Stars | 131 | 131 | 136 |
| Language | JavaScript | JavaScript | JavaScript |
| Last pushed | — | — | 2026-06-27 |
| Maintenance | — | — | Active |
| Setup difficulty | easy | easy | easy |
| Complexity | 2/5 | 2/5 | 2/5 |
| Audience | general | pm founder | developer |
Figures from each repo's GitHub metadata at analysis time.
AI Path is a free, interactive course that teaches artificial intelligence from scratch to beginners. It covers 30 lessons across 6 stages, from "what is a neural network" all the way to building a working AI application yourself. No signup is required, and you can access every lesson directly at aipath.buynao.com. The course is built around the idea of intuition before formulas. Each concept gets introduced through a plain-language analogy, then reinforced with an interactive demo you can actually play with in your browser. You can drag a neuron's weights, turn a temperature knob to see how an AI picks its next word, or roam through a 3D space of word vectors. The goal is that by the time you encounter a technical term, you already have a mental picture of what it means. The six stages move through: understanding what AI is, the building blocks of deep learning like attention and transformers, how large language models are trained, how to put them to work with prompting and retrieval, newer topics like image generation and reasoning models, and finally hands-on practice where you call a real API, run a model on your own machine, and build a small knowledge base. Each lesson takes about 20 minutes. The site is fully bilingual in Chinese and English. A toggle on the page switches the entire site, including all lesson text, demos, and quizzes, without a page reload. Technically, the course runs as a Vite and React application. If you want to run it locally, you clone the repository, install dependencies with npm, and start a dev server. The 30 lessons are each a self-contained React component with their own visualization code for canvas, SVG, and three.js animations. The whole course was built using an AI coding tool, which the README notes explicitly. The project is open for anyone to read or contribute to.
A free, bilingual interactive course that teaches AI from the basics through 30 hands-on lessons with browser-based demos, no signup required.
Mainly JavaScript. The stack also includes JavaScript, React, Vite.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly general.
This repo across BitVibe Labs
Verify against the repo before relying on details.