RepoAlerts
SponsorGet alerts

SakanaAI/AI-Scientist-v3

Get alerts like thisView on GitHubShare on X

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 9 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 2 days ago.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

Orchestrates coding agents that draft a task, propose and run experiments, evaluate results against a task rubric, run baselines and ablations, and write a paper, keeping every stage under one run directory. Driven by task.md files, with Docker as the default runtime.

Who it's for

Researchers and developers automating experiment pipelines with coding agents such as Claude, Codex, or Gemini

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up SakanaAI/AI-Scientist-v3 in my project. Follow its README: https://github.com/SakanaAI/AI-Scientist-v3. Explain each step and check it is safe before running anything.

Read the README

Star curve

430From 0 to 430 stars between 11 Oct 2026 and 20 Oct 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

18,265 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![SakanaAI/AI-Scientist-v3 on RepoAlerts](https://repoalerts.com/badge/SakanaAI/AI-Scientist-v3.svg)](https://repoalerts.com/repo/SakanaAI/AI-Scientist-v3?ref=badge)
Share on X
  • AI4AI-for-Anything/ResearchBoost-Agent

    An autonomous agent that profiles bottlenecks in AI training code, implements optimizations, and validates speedups against a frozen judge that checks bitwise equivalence and statistical training equi

    AI agentsPython · 71 stars · +71 this week · 2 days old

  • Gen-Verse/DiscoveryRSI

    A Python harness for recursive, hypothesis-centred research workflows in life science. It runs multi-agent hypothesis development, records revision lineage and evidence, compiles selected investigatio

    AI agentsPython · 113 stars · +113 this week · 6 days old

  • aicodeking/pandacode

    A native desktop app that runs multiple coding agent CLIs side by side (Claude Code, Codex, OpenCode and others) with projects, Git, worktrees, a terminal and a browser in one window. Tasks are organi

    Apps & desktopRust · 155 stars · +155 this week · 3 days old

  • Aoisop/mawoagent

    A local Python agent runtime with a web workbench and CLI that connects model inference, tool execution, permission checks, session resume, long-term memory and Skills. It can turn explicit user feedb

    AI agentsPython · 57 stars · +56 this week · 2 days old

  • iha2/superlite

    A Claude Code plugin that plans a software build, splits it into tasks that run in parallel, assigns each task to a model by difficulty, checks the seams between parts and reviews the result. The user

    AI agentsPython · 172 stars · +172 this week · 3 days old

  • vxcontrol/pentagi

    Self-hosted multi-agent system that autonomously plans and runs penetration testing tasks from a plain-language target and goal. Agents use 20+ security tools such as nmap, Metasploit and sqlmap insid

    AI agentsGo · 31,516 stars · +3,316 this week · 652 days old