Claude Skill

aiming-lab/AutoResearchClaw

AutoResearchClaw is a fully autonomous, self-evolving research system that turns a chat idea into a complete scientific paper. Features multi-agent debate, citation verification, and end-to-end pap...

Overview

Stars13,683
Forks1,598
LanguagePython
Last pushed2026-06-03
Last synced2026-07-03
View on GitHub

Repository

Owneraiming-lab
RepositoryAutoResearchClaw
Full nameaiming-lab/AutoResearchClaw
Repo ID1,182,108,611

Install this Skill

pip install -e . && researchclaw setup && researchclaw init && researchclaw run --topic "Your research idea here" --auto-approve

Registry

Typemcp_server
Quality score85/100
Verificationreadme_parsed
Last verified2026-05-28
Platforms
ClaudeMCPOpenClawCodex
Capabilities
browserpdfmemorysearchimageterminalworkflowautonomous-researchcitation-verificationllm-agents
Detected files
README.mddocspyproject.tomltests
Config keys
OPENAI_API_KEYURLTAVILY_API_KEY
Install methods
  • pip install -e . && researchclaw setup && researchclaw init && researchclaw run --topic "Your research idea here" --auto-approve
  • git clone https://github.com/aiming-lab/AutoResearchClaw.git
  • pip install -e .
  • pip install metaclaw

Summary

AutoResearchClaw is a fully autonomous, self-evolving research system that transforms a chat idea into a complete scientific paper. Built with Python and leveraging LLM agents, multi-agent debate, and citation verification, it enables end-to-end paper generation without human intervention.

Chinese description

从创意到论文的完全自主研究。聊天提出想法,即刻获得论文。全程自动化。🦞

Key features

  • Fully autonomous paper generation from idea to publication-ready output
  • Multi-agent debate for rigorous scientific reasoning and validation
  • Built-in citation verification to ensure reference accuracy
  • Self-evolving research pipeline that improves over time
  • Supports scientific discovery and open research workflows

Use cases

  • Rapid prototyping of research ideas into draft papers
  • Automated literature review and citation management
  • Collaborative multi-agent scientific reasoning
  • Self-improving research assistant for academics
  • Open science and reproducible research workflows

README excerpt

<p align="center"> <img src="image/logo.png" width="700" alt="AutoResearchClaw Logo"> </p> <h2 align="center"><b>Chat an Idea. Get a Paper. Autonomous, Collaborative & Self-Evolving.</b></h2> <p align="center"> <b><i><font size="5">Just chat with <a href="#openclaw-integration">OpenClaw</a>: "Research X" → done.</font></i></b> </p> <p align="center"> 📄 <b>Our paper is on arXiv — come read it!</b> <a href="https://arxiv.org/abs/2605.20025"><i>AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration</i></a> </p> <p align="center"> <img src="image/framework_v2.png" width="100%" alt="AutoResearchClaw Framework"> </p> <p align="center"> <a href="https://arxiv.org/abs/2605.20025"><img src="https://img.shields.io/badge/arXiv-2605.20025-b31b1b?logo=arxiv&logoColor=white" alt="arXiv"></a> <a href="https://huggingface.co/datasets/AIMING-Lab-UNC/ARC-Bench"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Dataset-ARC--Bench-yellow" alt="ARC-Bench on Hugging Face"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="MIT License"></a> <a href="https://python.org"><img src="https://img.shields.io/badge/Python-3.11%2B-3776AB?logo=python&logoColor=white" alt="Python 3.11+"></a> <a href="#testing"><img src="https://img.shields.io/badge/Tests-2699%20passed-brightgreen?logo=pytest&logoColor=white" alt="2699 Tests Passed"></a> <a href="https://github.com/aiming-lab/AutoResearchClaw"><img src="https://img.shields.io/badge/GitHub-AutoResearchClaw-181717?logo=github" alt="GitHub"></a> <a href="#openclaw-integration"><img src="https://img.shields.io/badge/OpenClaw-Compatible-ff4444?logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCI+PHBhdG

Topics

Explore more

Data from GitHub. Synced on 2026-07-03