# SakanaAI/AI-Scientist-v3

> Agentic Scientist orchestrates coding agents to autonomously run scientific experiments: from a task brief it generates ideas, runs experiments, ablations, a sealed evaluation, and writes a paper. The whole pipeline runs in Docker with a single run directory per experiment.

- Magnitude: 6.0 out of 10 — Early signal
- Stars: 131 total · +7 stars measured 2026-10-16, 00:10–00:48 UTC, ≈ 131 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-10-11 · Last push: 2026-10-15
- GitHub: https://github.com/SakanaAI/AI-Scientist-v3 · Page: https://gitnova.dev/en/r/SakanaAI/AI-Scientist-v3

## Useful for

- Run a full experiment pipeline from a task brief, getting a compiled paper
- Compare multiple coding agents on the same task by switching agent.name and agent.model
- Inspect run outputs and logs in a browser to audit ideas and results

## Why it’s here

- Star-counter measurements on 2026-10-16 (UTC), 00:10–00:48: 124 → 131 stars (+7). This is the change over that interval.
- Estimated end-of-day forecast: about +131 stars, using observed gains and the previous day.
- The repository is 5 days old and already has 131 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #127.
- About 36 forks a day — people are taking the code.
- Recent forks include notable developers: @HarleyCoops (216 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 15
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 44 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 10

## Stars per day, last 6 days (oldest → newest, today is partial)

2026-10-11 … 2026-10-16: 0, 0, 0, 3, 128, 7

## Magnitude by day, last 2 days

10-15 2.3, 10-16 6.0

## Spotted in now

- Top new repositories this week: #127

## More in this category

1. **anthropics/claude-plugins-official** — 7.4 · Breakout · AI agents · Python · +34 stars measured 2026-10-16, 00:05–00:48 UTC, ≈ 944 by evening
   Official Anthropic-managed directory of Claude Code plugins: internal plugins plus third-party ones from partners, installable via the built-in marketplace.
   Full card: https://gitnova.dev/en/r/anthropics/claude-plugins-official.md
2. **morluto/rea** — 6.3 · Peaking · AI agents · TypeScript · +636 stars measured 2026-10-16, 00:04–00:48 UTC, ≈ 18,847 by evening
   A reverse-engineering tool that lets AI agents inspect apps and native binaries: it connects agents to Hopper or Ghidra via MCP and CLI, helping explain how a feature works and rebuild it in your own project.
   Full card: https://gitnova.dev/en/r/morluto/rea.md
3. **xerj-org/xerj** — 6.1 · Breakout · AI agents · Rust · +29 stars measured 2026-10-16, 00:05–00:48 UTC, ≈ 1,033 by evening
   A local Rust search engine that auto-indexes folders of code, docs, logs and PDFs so AI agents retrieve exact passages instead of reading whole files. Elasticsearch-compatible and cuts token usage for agents.
   Full card: https://gitnova.dev/en/r/xerj-org/xerj.md
4. **heqiangdiao-wq/AI-Cross-Border-Ecommerce-Agent-Toolkit** — 6.0 · Early signal · AI agents · Python · +3 stars measured 2026-10-16, 00:05–00:48 UTC, ≈ 141 by evening
   A toolkit of 7 AI agent workflows built from prompts and templates that turn cross-border ecommerce SOPs for Shopee and Mercado Livre into repeatable operations: market research, product strategy, listing, images, video, ads and review…
   Full card: https://gitnova.dev/en/r/heqiangdiao-wq/AI-Cross-Border-Ecommerce-Agent-Toolkit.md
5. **pro-vi/cc-stretch** — 5.9 · Early signal · AI agents · TypeScript · +1 star measured 2026-10-16, 00:05–00:48 UTC, ≈ 184 by evening
   A Claude Code plugin that collapses long replies into short phrases: clicking a phrase expands it in place, clicking «« shrinks it back. It implements Ted Nelson's stretchtext idea so you read less without losing context.
   Full card: https://gitnova.dev/en/r/pro-vi/cc-stretch.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-16 00:59 UTC, updated every 30 minutes.