AutoResearch-Factory/Agon

35 stars · Last commit 2026-08-02

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.

README preview

# Agon

### Claude Code plugin for autonomous AI research — from a bare topic to running experiments, with no human-written experimental code

[![Project page](https://img.shields.io/badge/project-page-1f6feb.svg)](https://haizhaoyang.github.io/research/autoresearch.html)
[![arXiv](https://img.shields.io/badge/arXiv-2606.24177-b31b1b.svg)](https://arxiv.org/abs/2606.24177)
[![Claude Code](https://img.shields.io/badge/Claude%20Code-plugin-8A2BE2.svg)](https://claude.com/claude-code)

English | [中文](README_zh.md)

**Agon** ([paper](https://arxiv.org/abs/2606.24177)) takes a research project from a one-line topic to running experiments. Agents plan, implement, audit and review each other in closed loops, and every handoff goes through a file on disk — so a run is recoverable, auditable, and reusable across projects. The workflow stays minimal and explicit: `topic → idea → proposal → experiment`.

Agon is built on [**Prompt Economy**](https://arxiv.org/abs/2606.08878): treat prompt engineering as engineering, and minimize the engineering effort it demands from humans. See the [paper](https://arxiv.org/abs/2606.24177) for deployment details across more than ten research domains.

![Agon workflow](figures/figure_xp.png)

## Quick start

Clone [Agon](https://github.com/AutoResearch-Factory/Agon) and [agon-artifacts](https://github.com/AutoResearch-Factory/agon-artifacts):

View full repository on GitHub →