AI-Scientist-v2 vs EvoScientist

The two are close in size: 7.1k stars for AI-Scientist-v2, 4.6k for EvoScientist. Over the days we have tracked them AI-Scientist-v2 moved +2.7% and EvoScientist +7.2%, so EvoScientist is growing faster right now.

EvoScientist leads on customization. AI-Scientist-v2 does not take any axis by a clear margin.

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

End-to-end autonomous scientific discovery: it uses progressive agentic tree search to ideate, run experiments, analyze results, and draft papers without human-authored templates.

Stars
7.1k
Tracked growth
+2.7%
Maturity
Last commit
260d ago
Language
Python
License
NOASSERTION
Cost to run
Your API key, per-run (README cites ≈$15–$20 for experiments + ≈$5 for writing with default models)

Auto-distills a growing memory/knowledge graph into reusable AutoSkills and a multi-agent research loop, enabling long-running self-evolving AI scientists.

Stars
4.6k
Tracked growth
+7.2%
Maturity
Last commit
3h ago
Language
Python
License
Apache-2.0
Cost to run
Requires your cloud model API keys (per-use billing)
0%+7%45 tracked days
SakanaAI/AI-Scientist-v2EvoScientist/EvoScientist

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.

AxisAI-Scientist-v2EvoScientist
Context depth
How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository.
Related files
Diff + related files
Noise control
How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only.
Config-based controls
Basic filtering & gating
Customization
How far it bends to your team: custom rules, prompts, style guides, per-path config.
Configurable params
Extensible skills & config
Privacy
Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only.
Cloud APIs (your keys)
Self-hostable
Model freedom
Whether you can point it at any provider, or it is wired to one.
Multiple providers
Multiple cloud providers
Setup ease
What it takes to get a first useful run out of it.
GPU install required
Config + API key

Which one to pick

Pick AI-Scientist-v2 if…

End-to-end autonomy — pick this when you want a research pipeline that generates hypotheses, executes experiments, and produces writeups using configurable agentic tree search across multiple LLM providers.

Runs in cli. Works with openai, anthropic, gemini.

Pick EvoScientist if…

Self-evolving research — pick EvoScientist when you want an opinionated, multi-agent system that autonomously builds a persistent knowledge graph and drafts reusable skills for iterative scientific workflows.

  • Customization: Extensible skills & config (5/5 against 3/5)
Runs in cli, web-app. Works with byok, openai, anthropic, other-fixed.

What people want from each one

Questions people ask

Is AI-Scientist-v2 better than EvoScientist?

EvoScientist leads on customization. AI-Scientist-v2 does not take any axis by a clear margin. AI-Scientist-v2 is worth picking when end-to-end autonomy — pick this when you want a research pipeline that generates hypotheses, executes experiments, and produces writeups using configurable agentic tree search across multiple LLM providers.

Which of AI-Scientist-v2 and EvoScientist keeps my code private?

AI-Scientist-v2: Cloud APIs (your keys) (3/5). EvoScientist: Self-hostable (4/5).

What does each one cost to run?

AI-Scientist-v2: Your API key, per-run (README cites ≈$15–$20 for experiments + ≈$5 for writing with default models). EvoScientist: Requires your cloud model API keys (per-use billing).

Full profiles: SakanaAI/AI-Scientist-v2 and EvoScientist/EvoScientist. Everything else in ML experiment agents.