Claude Autoresearch Skill -- Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify - Verify - Keep/Discard - Repeat forever.
-
Updated
Mar 16, 2026
#
karpathy
Here are 48 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies
machine-learning ai deep-learning csharp neural-network dotnet autograd transformer gpt language-model backpropagation karpathy
-
Updated
Feb 14, 2026 - C#
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.
python nlp deep-learning neural-network tokenizer jupyter-notebook pytorch transformer educational gpt lecture language-model pytorch-tutorial karpathy andrej neural-networks-from-scratch pytorch-implementation micrograd zero-to-hero nn-zero-to-hero
-
Updated
Feb 28, 2026 - Jupyter Notebook
GPT in a QR Code ; The actual most atomic way to train and inference a GPT in pure, dependency-free JS/Python.
javascript python machine-learning ai artificial-intelligence minification gpt karpathy microgpt decompressionstream picogpt
-
Updated
Feb 17, 2026 - HTML
Train Llama 3 models from scratch. Any scale, any personality. By Arianna Method.
training go golang machine-learning ai deep-learning transformers pytorch transformer llama from-scratch personality karpathy llm llamacpp gguf llama3 nanochat nanollama
-
Updated
Feb 25, 2026 - Python
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
javascript typescript linting linter static-analysis developer-tools code-review code-quality copilot karpathy ai-tools ai-generated-code ai-detection
-
Updated
Dec 7, 2025 - TypeScript
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.
python c-plus-plus parallel-computing transformers gpu-acceleration gpt karpathy deep-learning-from-scratch cuda-programming gpt-2 mingpt llm
-
Updated
Mar 5, 2026 - HTML
Train your own ChatGPT on Apple Silicon -- MLX port of nanochat
training macos machine-learning deep-learning transformer gpt language-model mlx karpathy sft apple-silicon llm chatgpt nanochat
-
Updated
Mar 7, 2026 - Python
A self-contained course to learn the basics of neural networks: from backprop to GPT!
python learning machine-learning tutorial course ai guide pytorch transformer neural-networks gradients gpt notebooks lecture karpathy micrograd zero-to-hero
-
Updated
Jan 28, 2026 - Jupyter Notebook
Transcripts of the Neural Networks: Zero to Hero course
learning education lectures course ai openai neural-networks transcripts whisper karpathy andrej notebook-jupyter zero-to-hero
-
Updated
Feb 29, 2024
Interactive GPT/Transformer Learning Platform -- Interaktif GPT/Transformer Egitim Platformu
react visualization nlp education machine-learning tutorial deep-learning neural-network interactive transformer gpt attention-mechanism karpathy ai-education
-
Updated
Mar 2, 2026 - JavaScript
Solutions for Andrej Karpathy's "Neural Networks: Zero to Hero" course
-
Updated
Mar 3, 2024 - Jupyter Notebook
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.
open-source ai deep-learning csharp unity automatic-differentiation unity3d regression autograd artificial-intelligence neural-networks classification karpathy micrograd
-
Updated
Oct 14, 2025 - C#
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.
engineering automation ai skills eval agents autonomous-agents karpathy claude self-improving llm prompt-engineering enterprise-ai openclaw autoresearch overnight-training
-
Updated
Mar 15, 2026 - HTML
GPT code - I completed the tutorial for building GPT components by Andrej Karpathy (Let's build GPT: from scratch, in code, spelled out)
nlp jupyter-notebook python3 pytorch attention gpt language-model attention-mechanism autoregressive karpathy self-attention llm llms chat-gpt
-
Updated
Sep 23, 2023 - Jupyter Notebook
OpenClaw Skill: Daily AI/Tech digest from 92 Karpathy-curated blogs. Zero deps, no API keys. Agent-native RSS - Score - Summarize pipeline.
-
Updated
Feb 25, 2026 - JavaScript
This repository is dedicated to my learning journey through the AI Neural Network Course by Andrej Karpathy. It contains my personal notes, code snippets, and key takeaways from the first four parts of the course.
-
Updated
Mar 13, 2024 - Jupyter Notebook
A random thought experiment on Infinite Monkey Theorem.
-
Updated
Apr 2, 2023 - Python
An AI research partner that figures out what to measure and how to test it. Live dashboard and actionable results. Built on Karpathy's autoresearch.
automation research ai gemini experiments codex autonomous-agents ai-agents karpathy claude claude-code autoresearch
-
Updated
Mar 16, 2026 - TypeScript
Improve this page
Add a description, image, and links to the karpathy topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the karpathy topic, visit your repo's landing page and select "manage topics."