Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies

Detailed python notes & code for lectures and exercises of Andrej Karpathy's course "Neural Networks: Zero to Hero." The course is focused on building neural networks from scratch.

GPT in a QR Code ; The actual most atomic way to train and inference a GPT in pure, dependency-free JS/Python.

Train Llama 3 models from scratch. Any scale, any personality. By Arianna Method.

⚡ The AI Slop Index linter inspired by @karpathy. Detects hallucinated imports, any-type abuse, vibe coding, and soul-less patterns in TypeScript/JavaScript/React. Fast (~4s), educational, CI-ready. npx karpeslop@latest

Train your own ChatGPT on Apple Silicon — MLX port of nanochat

🔬 The most atomic GPT-2 implementation in 265 lines of pure Python & CUDA. A bilingual "Rosetta Stone" for understanding LLM internals from scratch. No dependencies, just math and kernels.

The Karpathy treatment for OpenClaw - stripped to ε. 515 lines of Python, 6 files, one dependency.

📖 A self-contained course to learn the basics of neural networks: from backprop to GPT! 🌻

Transcripts of the Neural Networks: Zero to Hero course

Solutions for Andrej Karpathy's "Neural Networks: Zero to Hero" course

🧠 Interactive GPT/Transformer Learning Platform — İnteraktif GPT/Transformer Eğitim Platformu

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.

Repository nanoGPT from @karpathy accelerated with JAX/Flax! The simplest, fastest repository for training/finetuning medium-sized GPTs.

Autonomous AI skill improvement through iterative experimentation — inspired by Karpathy's autoresearch. An agent mutates skill instructions, evaluates against objective metrics, keeps improvements, reverts regressions. No human in the loop.

Autonomous goal-directed iteration for Gemini CLI. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

Godmode: Autonomous AI coding powered by Karpathy's autoresearch principles. 126 skills, 7 subagents, 5 platforms. Keep/discard loops, TSV logging, zero config.

Companion tools for Karpathy's autoresearch - smarter evaluation, guided steering, and multi-agent competitions for GPT pretraining