TanStack
Featured
router
TanStack Router is a type-safe, data-driven React router with built-in caching, prefetching, and nested layouts, while TanStack Start extends it into a full-stack SSR framework.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It builds every component from scratch—BPE tokenizer, Word2Vec embeddings, and a full decoder-only transformer—without relying on ML libraries, making the inner workings of LLMs transparent and learnable.
Who it is for
- Developers curious about how LLMs work under the hood
- Machine learning students seeking hands-on, code-based learning
- Educators looking for interactive demos to illustrate NLP concepts
- Hobbyists who want to experiment with training small models locally
Use cases
- Learning the full lifecycle of an LLM through interactive demos
- Teaching backpropagation, tokenization, and transformer mechanics
- Prototyping small-scale models and visualizing training progress
- Comparing ELIZA-style patterns with learned neural approaches
Strengths
- Covers the complete pipeline from simple pattern matching to a full transformer
- All core implementations are written from scratch with no black-box ML libraries
- Interactive SSE streaming provides real-time visualization of training and tokenization
- References seminal papers for each section, grounding the code in research
Considerations
- Requires local setup with Node 20+ and pnpm, limiting instant browser-only use
- Training runs on CPU only and may be slow for larger datasets or experiments
- No pre-trained weights or deployment guidance—strictly educational and demonstrative
README quick start
How LLMs Work
An interactive app that walks through every stage of the LLM pipeline — from pattern matching to training a transformer from scratch — with working code you can run locally.
Stack
Setup
Requires pnpm and Node.js 20+.
pnpm install
pnpm dev
If pnpm reports ignored build scripts, run:
pnpm approve-builds
Select esbuild with Space, press Enter, then rerun pnpm install.
Sections
1. Simple Chat — Pattern Matching
The simplest possible "AI": an ELIZA-style chatbot that responds with if-statements, streamed word by word via SSE. Same plumbing as ChatGPT, zero intelligence.
2. XOR Neural Net — Backpropagation
Trains a neural network live. A single-layer perceptron fails on XOR (proving Minsky/Papert right). A multi-layer network succeeds via backpropagation — the same algorithm every neural network uses today.
- Route:
src/routes/neural-net/ - Hook:
src/client/hooks/use-neural-net-chat.tsx - Component:
src/client/components/neural-net-result/
3. Basic Tokenizer — BPE From Scratch
A from-scratch BPE implementation that trains on your input text. Watch merge steps animate as the algorithm builds a vocabulary from characters to words.
Description
An interactive app that walks through every stage of the LLM pipeline, from pattern matching to training a transformer from scratch, with working code you can run locally.
Related repositories
Similar projects matched by category, topics, and programming language.
vercel-labs
Featured
scriptc
scriptc compiles ordinary TypeScript into small, fast native executables without needing Node.js, V8, or any JavaScript runtime in the binary.
Jakubantalik
Featured
thinking-orbs
A React component library that renders six hand-tuned animated thought orb loading indicators on a plain 2D canvas, with two purpose-tuned sizes and automatic theme detection for AI and agent UIs.