autonomous-research 开源项目推荐（137 个）

aiming-lab /AutoResearchClaw

从想法到论文的全自主、自演进研究。聊一个想法，得一篇论文。🦞

OpenNSWM-Lab /FAROS

一个基于蓝图的自动研究运行时，用于协调从创意生成、实验到论文写作和同行评审等人工智能研究工作流程。

OpenRaiser /NanoResearch

🦞+🔬 NanoResearch: The Autonomous AI Research Assistant

ZimoLiao /scholaraio

Scholar All-In-One: A research infrastructure for AI agents

yogsoth-ai /de-anthropocentric-research-engine

900+纯折扣技能，用于自主AI研究，组织为9个可自由组合的包，分布在4层层级结构（战役→策略→战术 → SOP）。非线性编排带回溯，6个MCP集成。人工智能是研究者——你负责设定方向。

gaotiexinqu /OneResearchClaw

任何研究。一爪。🦞 从任何材料到研究，都有完全自主且技能驱动的研究人员。

Sibyl-Research-Team /AutoResearch-SibylSystem

具备自我进化能力的完全自主 AI 研究系统，原生构建于 Claude Code 之上

ProjectDXAI /labrat

自治多分支研究实验室。分支机构争夺计算预算。系统会逐渐趋同于有效的方法。

Shanghua-Gao /RSI-Jev

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.

AI4Scientist /nano-scientist

An autonomous research agent that turns a topic into a peer-reviewed technical report

smileformylove /XScientist

Turn ideas into autonomous research with Git-like evidence histories—inspectable, reproducible, and reversible.

YihongT /CoAutoResearch

An open-source research system for autonomous investigation, recursive self-improvement, and human–AI collaboration. Run experiments, refine methods through evidence and feedback, and turn traceable research into paper drafts.

Omni-Scientist /Awesome-AI-Scientist

🧪 Awesome list of AI Scientist papers, systems, benchmarks, datasets and open-source platforms.

Usaid22 /swarm-factory

Top Autonomous Research Multi-Agent System for 2026 Lab Experiments

AutoResearch-Factory /Agon

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.

Araaf7 /swarm-factory

Top Autonomous Research Multi-Agent System for 2026 Lab Experiments

zjunlp /AutoSciRub

Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents

hanlulong /econ-auto-research

该项目在 GitHub 上没有填写描述

qrzou /FML-bench

FML-bench

paperfoot /autoresearch-cli

Autonomous AI experiment loop CLI -- run research overnight with any coding agent