# SakanaAI/AI-Scientist

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Repository: https://github.com/SakanaAI/AI-Scientist
Canonical: https://ross.abutalabs.com/products/ai-scientist
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Last push: 2025-12-19T07:46:21+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 58, release rhythm 35, longevity 53
- inputs: {"age_days": 751, "days_push": 257, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14449, forks 2047 (observed 2026-08-28T04:11:07.045531+00:00)

## What it is
The AI Scientist is a system that uses large language models to autonomously perform end-to-end scientific research, from idea generation and experiment execution to writing and reviewing papers. It is a research framework from Sakana AI demonstrating fully automated open-ended scientific discovery.

## Use cases
- automatically generate and run machine learning research ideas
- have an LLM write full research papers end to end
- automate the scientific discovery pipeline
- run autonomous AI research agents on experiment templates
- generate and review papers with foundation models

## When to choose
- you want to explore fully automated AI-driven research pipelines
- you need a reference implementation of LLM agents doing experiments and paper writing
- you are studying autonomous scientific discovery with foundation models

## When to avoid
- you need production-grade, reliable ML tooling rather than experimental research demos
- you cannot afford significant LLM API and GPU costs
- you require human-supervised, peer-reviewed research output

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, machine-learning, data-science
- domain: artificial-intelligence, large-language-models, data-science
- platform: python
- tags: automated-research, paper-generation, scientific-discovery, llm-agents, ai-agents, research, linux, gpu

## Member repositories
- SakanaAI/AI-Scientist (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:07.045531+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:12:33.488226+00:00, confidence not recorded.
  - readme: https://github.com/SakanaAI/AI-Scientist (fetched 2026-08-28T04:11:07.045531+00:00, sha 55527bacdbc2)
- Data as of 2026-08-30T08:39:29.467469+00:00.