7 Karpathy repos that take you from one neuron to autonomous AI research
atullchaurasia · x · 2026-11-03
A curated path through Andrej Karpathy's 7 learning repos: micrograd (18.6k stars, 100-line autograd engine), nn-zero-to-hero (25.3k, hands-on curriculum to transformers), minbpe (11k, minimal BPE tokenizer), nanoGPT (64.4k, clean minimal GPT), llm.c (31.4k, GPT-2 in raw C/CUDA), nanochat (60.1k, full hackable LLM pipeline), and autoresearch (13.7k, an agent that edits training code and runs 100 experiments overnight).
More from coding & agent
- LetterBox adds granular API key permissions, agents can create Drafts over MCP — rchardkovacs · 2026-11-03
- Tsinghua study: continual harness self-evolution causes severe catastrophic forgetting in coding agents — Shangziqi Zhao · 2026-11-03
- Vantage: open-source Windows app lets AI agents drive your real desktop, 80-step task in ~8 min — AKGAMING1234 · 2026-11-03
- Reward hacking risks when agents optimize inference, new article warns — AccBalanced · 2026-11-03
- Build a Media Agent workshop: CPU-based agent calling GPU tools on demand — Al_Grigor · 2026-11-03
- Factory rebuilt its Droid coding agent to run inside customers' own clouds, plans to open source the compute layer — AI Engineer · 2026-11-03