#15 by GitHub stars · Research
autoresearch
Andrej Karpathy
An experimental agent loop that changes training code, runs short experiments, and keeps improvements to a small language model.
View on GitHub 97k stars checked 2026-09-29
- Access
- Open source
- Setup
- Technical
- Pricing
- Free software; substantial GPU costs
- License
- MIT
- Maintenance
- Limited recent activity
- Last repository push
- 2026-03-26
Compelling but highly specialized
It is a clear, minimal example of an agent conducting measurable machine-learning experiments autonomously.
Who it fits
ML researchers with suitable NVIDIA hardware who want a controlled autonomous experimentation baseline.
Who should skip it
General research, consumer tasks, or users without a strong GPU and ML engineering experience.
What you need
- NVIDIA GPU tested on H100
- Python 3.10+ and uv
- ML experiment supervision
Similar agents
Compare before you commit
These alternatives are maintained as editorial relationships, then checked against the current catalog.
| Agent | Access | Setup | Pricing | Best for | Popularity | Primary link |
|---|---|---|---|---|---|---|
| autoresearchCurrent | Open source | Technical | Free software; substantial GPU costs | ML researchers with suitable NVIDIA hardware who want a controlled autonomous experimentation baseline. | 97k stars | GitHub |
| DeerFlow | Open source | Technical | Free software; model and search costs | Technical researchers and teams that want a configurable, locally controlled multi-step research workflow. | 83.2k stars | GitHub |
| BettaFish | Open source | Technical | Free repository; model, API, or hosting costs may apply | People evaluating popular open GitHub projects for research use cases. | 42.3k stars | GitHub |
| storm | Open source | Technical | Free repository; model, API, or hosting costs may apply | People evaluating popular open GitHub projects for research use cases. | 31.5k stars | GitHub |