A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Repository Index
132,241 visible repositories in the index
1–24 of 102 · Most stars
AI agents running research on single-GPU nanochat training automatically
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
- claude-code
- claude-skills
- understandcode
- codex
The simplest, fastest repository for training/finetuning medium-sized GPTs.
The best ChatGPT that $100 can buy.
LLM training in simple, raw C/CUDA
LLM Council works together to answer your hardest questions
Neural Networks: Zero to Hero
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Inference Llama 2 in one file of pure C
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.
- claude-code
- obsidian
- second-brain
- claude-code-skill
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
Moveable! Draggable! Resizable! Scalable! Rotatable! Warpable! Pinchable! Groupable! Snappable!
- moveable
- movable
- draggable
- resizable
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspired by Karpathy and 3Blue1Brown for moving beyond prompt engineering to the wider discipline of context design, orchestration, and optimization.
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
Projects for an undergraduate OS course
Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK.
- healthcare
- llm
- on-device
- on-premise
Web interface for browsing, search and filtering recent arxiv submissions
Video+code lecture on building nanoGPT from scratch
Efficient Image Captioning code in Torch, runs on GPU
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.