AI-Scientist vs Auto-claude-code-research-in-sleep
The two are close in size: 14.5k stars for AI-Scientist, 15.7k for Auto-claude-code-research-in-sleep. Over the days we have tracked them AI-Scientist moved +1.6% and Auto-claude-code-research-in-sleep +14.6%, so Auto-claude-code-research-in-sleep is growing faster right now.
They split the axes: AI-Scientist leads on model freedom, Auto-claude-code-research-in-sleep on noise control and customization.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
Automates end-to-end scientific discovery by generating hypotheses, running experiments, and producing full LaTeX papers from templates.
- Stars
- 14.5k
- Tracked growth
- +1.6%
- Maturity
- ●●●●●
- Last commit
- 260d ago
- Language
- Jupyter Notebook
- License
- NOASSERTION
- Cost to run
- Requires your API keys for cloud models; local GPU needed for open-weight runs.
Provides a lightweight, skill-based autonomous research workflow with built-in cross-model reviewer loops and deterministic integrity audits (Anti-Autoresearch), targeted at reproducible ML research rather than generic agent tasks.
- Stars
- 15.7k
- Tracked growth
- +14.6%
- Maturity
- ●●●●●
- Last commit
- 2d ago
- Language
- Python
- License
- MIT
- Cost to run
- Your API key or model subscription
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | AI-Scientist | Auto-claude-code-research-in-sleep |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Template-level view | ●●●●● Diff + related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Ensemble reviews | ●●●●● Severity gating & audits |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Template + prompt config | ●●●●● Skill & per-call config |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable (local GPU) | ●●●●● Cloud APIs (your key) |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● BYOK + local models | ●●●●● Several providers |
Setup ease What it takes to get a first useful run out of it. | ●●●●● GPU + dependencies | ●●●●● Config + API key |
Which one to pick
Pick AI-Scientist if…
End-to-end experiment automation — pick this when you want a research-focused system that generates ideas, runs experiments on local GPUs, and compiles full papers automatically.
- Model freedom: BYOK + local models (5/5 against 3/5)
Pick Auto-claude-code-research-in-sleep if…
Research-focused — pick ARIS when you need an audited, multi-model research automation stack with reviewer gating, integrity checks, and per-skill customization.
- Noise control: Severity gating & audits (5/5 against 3/5)
- Customization: Skill & per-call config (5/5 against 3/5)
What people want from each one
SakanaAI/AI-Scientist
wanshuiyin/Auto-claude-code-research-in-sleep
Questions people ask
Is AI-Scientist better than Auto-claude-code-research-in-sleep?
They split the axes: AI-Scientist leads on model freedom, Auto-claude-code-research-in-sleep on noise control and customization. AI-Scientist is worth picking when end-to-end experiment automation — pick this when you want a research-focused system that generates ideas, runs experiments on local GPUs, and compiles full papers automatically.
Which of AI-Scientist and Auto-claude-code-research-in-sleep keeps my code private?
AI-Scientist: Self-hostable (local GPU) (4/5). Auto-claude-code-research-in-sleep: Cloud APIs (your key) (3/5).
What does each one cost to run?
AI-Scientist: Requires your API keys for cloud models; local GPU needed for open-weight runs.. Auto-claude-code-research-in-sleep: Your API key or model subscription.
Full profiles: SakanaAI/AI-Scientist and wanshuiyin/Auto-claude-code-research-in-sleep. Everything else in ML experiment agents.