What Is AutoResearch?
AutoResearch is a lightweight autonomous research loop for language model training. Instead of manually tuning everything yourself, you let an AI coding agent test changes, run short training jobs, compare outcomes, and keep iterating.
If you searched for autoresearch github, karpathy autoresearch, or autoresearch ai, this is the project most people currently mean: karpathy/autoresearch.
Why Is AutoResearch Trending?
People are paying attention because the project combines several themes that are hot right now:
- AI coding agents modifying code autonomously
- compact training loops that are easier to understand than giant ML stacks
- fixed-time experiments that make iteration easier to compare
- a workflow centered on guiding agents with instructions instead of hand-editing everything
The other reason is simple: the project comes from Andrej Karpathy, so many developers search the repo name directly before a broader ecosystem of tutorials and documentation exists.
How AutoResearch Works
The repository is intentionally small. The core workflow revolves around three files and a tight experiment loop.
prepare.py handles data preparation, tokenizer setup, and runtime utilities.
train.py is the main file the agent is expected to change while exploring model and optimization ideas.
program.md acts like an instruction sheet for the agent, shaping how it should reason about experiments.
Quick Facts
Requirements and Limitations
The original repository is built around a single NVIDIA GPU workflow, and the README notes it was tested on H100-class hardware. That does not mean smaller setups are impossible, but it does mean you should expect tradeoffs if you are running on a Mac, consumer GPU, or lower-compute machine.
- smaller datasets are often more practical on limited hardware
- lower sequence lengths can reduce memory pressure
- smaller vocabularies and lower model depth may be necessary
- forks may be more useful than the default setup on non-NVIDIA environments
Forks and Smaller-Hardware Options
One reason this project is interesting for searchers is that the ecosystem is already branching out. The original repository points to notable forks for MacOS, Windows, and AMD.
If your real question is not "What is AutoResearch?" but "Can I run something like this on my machine?", you will probably want to explore forks and reduced-compute adaptations instead of using the defaults unchanged.
Useful Links
FAQ
What is AutoResearch?
AutoResearch is an open-source project that lets AI agents run repeated ML training experiments inside a compact codebase.
Where is the AutoResearch GitHub repository?
The repository most people are looking for is github.com/karpathy/autoresearch.
Can AutoResearch run on Mac or smaller hardware?
Not with the original defaults in every case. Many people look to forks and lower-compute adaptations for Mac, Windows, AMD, and smaller GPUs.
Is AutoResearch the same as AutoRA?
No. They are different projects.
Is this an official site?
No. This is an unofficial fan-made guide and is not affiliated with Andrej Karpathy or the project maintainers.