by karpathy · Agent Tool · ★ 59.6k
autoresearch One day, frontier AI research used to be done by meat computers in between eating, sleeping, having other fun, and synchronizing once in a while using sound wave interconnect in the ritual of "group meeting". That era is long gone. Research is now entirely the domain of autonomous swarms of AI agents running across compute cluster megastructures in the skies. The agents claim that we are now in the 10,205th generation of the code base, in any case no one could tell if that's right or wrong as the "code" is now a self-modifying binary that has grown beyond human comprehension. This repo is the story of how it all began. -@karpathy, March 2026. The idea: give an AI agent a small but real LLM training setup and let it experiment autonomously overnight. It modifies the code, trains for 5 minutes, checks if the result improved, keeps or discards, and repeats. You wake up in the morning to a log of experiments and (hopefully) a better model. The training code here is a simplified single-GPU implementation of nanochat. The core idea is that you're not touching any of the Python files like you normally would as a researcher.
| Stars | 59,576 |
| Forks | 8,265 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 48.47/100 |
| Open Issues | 161 |
| Last Updated | 2026-03-26 |
| Created | 2026-03-06 |
| Platforms | python |
| Est. Tokens | ~36k |
Explore other popular agent tool tools:
autoresearch is AI agents running research on single-GPU nanochat training automatically. It is categorized as a Agent Tool with 59.6k GitHub stars.
autoresearch is primarily written in Python.
You can find installation instructions and usage details in the autoresearch GitHub repository at github.com/karpathy/autoresearch. The project has 59.6k stars and 8265 forks, indicating an active community.