# nanochat

nanochat is the simplest experimental harness for training LLMs. It is designed to run on a single GPU node, the code is minimal/hackable, and it covers all major LLM stages including tokenization, pretraining, finetuning, evaluation, and inference.

- Tier: Indexed (plain plugin)
- Category: Development
- Page: https://www.flowy.sh/listings/karpathy-nanochat
- Source: https://github.com/karpathy/nanochat
- Price: free and open source

## Summary
nanochat is a Claude Code plugin with 1 hand-picked skill for development work, indexed on Flowy. Install it with the command on its page. It includes read-arxiv-paper. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

## Install (Claude Code)
```
npx -y skills add karpathy/nanochat --agent claude-code
```

## Skills
- read-arxiv-paper

## FAQ

### What is nanochat?
nanochat is the simplest experimental harness for training LLMs. It is designed to run on a single GPU node, the code is minimal/hackable, and it covers all major LLM stages including tokenization, pretraining, finetuning, evaluation, and inference.

### How do I install nanochat?
Run these in Claude Code: npx -y skills add karpathy/nanochat --agent claude-code. Then prompt normally.

### Does nanochat auto-invoke its skills?
Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

### Is nanochat free?
Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.