Minimal AI-driven research engine: idea → literature review → experiment plan → paper draft
How to install nanoresearch?
openraiser/nanoresearch
$git clone https://github.com/openraiser/nanoresearchInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install nanoresearch by running `git clone https://github.com/openraiser/nanoresearch`, then use it for the current task and follow its documentation at https://github.com/openraiser/nanoresearch.
README.md
| 1 | <a id="top"></a> |
| 2 | |
| 3 | <div align="center"> |
| 4 | |
| 5 | <div style="margin: 20px 0;"> |
| 6 | <img src="imgs/logo.png" alt="NanoResearch Logo" width="500" style="border-radius: 20px;"> |
| 7 | </div> |
| 8 | |
| 9 | # NanoResearch |
| 10 | |
| 11 | <p> |
| 12 | <a href="README.md"><img src="https://img.shields.io/badge/🇨🇳_中文-1a1a2e?style=for-the-badge" alt="中文"></a> |
| 13 | <a href="README_en.md"><img src="https://img.shields.io/badge/🇺🇸_English-1a1a2e?style=for-the-badge" alt="English"></a> |
| 14 | </p> |
| 15 | |
| 16 | **端到端自主 AI 科研引擎 — 从研究想法到完整论文，全程自动化** |
| 17 | |
| 18 | <p> |
| 19 | <a href="https://github.com/OpenRaiser/NanoResearch"><img src="https://img.shields.io/badge/🔥_Project-Page-00d9ff?style=for-the-badge&logo=github&logoColor=white&labelColor=1a1a2e" alt="Project"></a> |
| 20 | <a href="https://github.com/OpenRaiser/NanoResearch/stargazers"><img src="https://img.shields.io/github/stars/OpenRaiser/NanoResearch?color=00d9ff&style=for-the-badge&logo=star&logoColor=white&labelColor=1a1a2e" alt="Stars"></a> |
| 21 | <a href="https://github.com/OpenRaiser/NanoResearch/issues"><img src="https://img.shields.io/badge/🐛_Issues-ff6b6b?style=for-the-badge&logo=github&logoColor=white&labelColor=1a1a2e" alt="Issues"></a> |
| 22 | </p> |
| 23 | |
| 24 | <p> |
| 25 | <img src="https://img.shields.io/badge/Python-3.10%2B-4ecdc4?style=for-the-badge&logo=python&logoColor=white&labelColor=1a1a2e" alt="Python"> |
| 26 | <img src="https://img.shields.io/badge/License-MIT-16A34A?style=for-the-badge&labelColor=1a1a2e" alt="License"> |
| 27 | <img src="https://img.shields.io/badge/Pipeline-9_Stage_Deep-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="Pipeline"> |
| 28 | <img src="https://img.shields.io/badge/Execution-Local_|_SLURM-0EA5E9?style=for-the-badge&labelColor=1a1a2e" alt="Execution"> |
| 29 | </p> |
| 30 | |
| 31 | <p> |
| 32 | <a href="#快速开始"><b>快速开始</b></a> · |
| 33 | <a href="#效果展示"><b>效果展示</b></a> · |
| 34 | <a href="#流水线"><b>流水线</b></a> · |
| 35 | <a href="#claude-code-模式"><b>Claude Code</b></a> · |
| 36 | <a href="#飞书机器人"><b>飞书机器人</b></a> |
| 37 | </p> |
| 38 | |
| 39 | </div> |
| 40 | |
| 41 | --- |
| 42 | |
| 43 | > 🔬 NanoResearch **真正运行计算实验**——它不仅生成代码，还能将代码提交到 GPU 集群执行训练，收集真实实验结果，生成论文配图，最终输出一篇有实验数据支撑的完整 LaTeX 论文。论文中的每一个数据、表格、图表都来自实际运行的实验结果，**而非 LLM 编造**。 |
| 44 | |
| 45 | --- |
| 46 | |
| 47 | ## 📖 目录 |
| 48 | |
| 49 | - [📊 论文实测展示](#-论文实测展示) |
| 50 | - [⚡ CLI 演示](#cli-demo) |
| 51 | - [📢 最新动态](#-最新动态) |
| 52 | - [✨ 核心特性](#-核心特性) |
| 53 | - [🆚 为何选择 NanoResearch](#-为何选择-nanoresearch) |
| 54 | - [🎯 应用场景](#-应用场景) |
| 55 | - [🖼️ 效果展示](#️-效果展示) |
| 56 | - [CLI：标准输出与 TUI 对比](#cli-tui-vs-plain) |
| 57 | - [🔬 流水线](#-流水线) |
| 58 | - [📦 快速开始](#-快速开始) |
| 59 | - [🧬 Evo 自进化流水线](#-evo-自进化流水线) |
| 60 | - [🧩 Claude Code 模式](#-claude-code-模式) |
| 61 | - [⚙️ 配置](#️-配置) |
| 62 | - [💻 CLI 参考](#-cli-参考) |
| 63 | - [🍪 示例与 Demo](#-示例与-demo) |
| 64 | - [📂 输出结构](#-输出结构) |
| 65 | - [💬 飞书机器人](#-飞书机器人) |
| 66 | - [🏗️ 项目结构](#-项目结构) |
| 67 | - [❓ 常见问题](#-常见问题) |
| 68 | - [🎯 路线图](#-路线图) |
| 69 | - [📋 环境要求](#-环境要求) |
| 70 | - [🙏 致谢](#-致谢) |
| 71 | - [🤝 贡献](#-贡献) |
| 72 | - [📝 引用](#-引用) |
| 73 | - [📄 许可证](#-许可证) |
| 74 | |
| 75 | <p align="right"><a href="#top">🔝 返回顶部</a></p> |
| 76 | |
| 77 | --- |
| 78 | |
| 79 | ## 📊 论文实测展示 |
| 80 | |
| 81 | 以下为 NanoResearch 自动生成论文中的**真实配图**，所有数据、曲线、表格均来自实际运行的实验结果，**非 LLM 虚构**。 |
| 82 | |
| 83 | <table> |
| 84 | <tr> |
| 85 | <td align="center" valign="top" width="33%"> |
| 86 | <img src="imgs/recognition_1.jpg" height="200" alt="实验结果"/> |
| 87 | <br /> |
| 88 | <sub><b>实验结果展示</b></sub> |
| 89 | </td> |
| 90 | <td align="center" valign="top" width="33%"> |
| 91 | <img src="imgs/recognition_2.jpg" height="200" alt="主结果对比"/> |
| 92 | <br /> |
| 93 | <sub><b>方法对比 / 主结果</b></sub> |
| 94 | </td> |
| 95 | <td align="center" valign="top" width="33%"> |
| 96 | <img src="imgs/recognition_3.jpg" height="200" alt="消融与可视化"/> |
| 97 | <br /> |
| 98 | <sub><b>消融与可视化</b></sub> |
| 99 | </td> |
| 100 | </tr> |
| 101 | </table> |
| 102 | |
| 103 | > 以上配图均为流水线自动生成，数据来源于真实训练日志与实验结果。 |
| 104 | |
| 105 | --- |
| 106 | |
| 107 | <a id="cli-demo"></a> |
| 108 | |
| 109 | ## ⚡ CLI 演示 |
| 110 | |
| 111 | NanoResearch **命令行（CLI）** 提供 **TUI 全屏界面** 与 **传统流式日志** 两种呈现方式。下方为 CLI 端 **TUI 主题与界面** 演示视频（配色切换与布局优化）。其他入口（如 Claude Code、飞书机器人）见文档对应章节。 |
| 112 | |
| 113 | <table> |
| 114 | <tr> |
| 115 | <th><p align="center">🖥️ CLI / TUI</p></th> |
| 116 | </tr> |
| 117 | <tr> |
| 118 | <td align="center"> |
| 119 | <video src="https://github.com/user-attachments/assets/008911c6-b015-47ff-a286-1d8c22f5817e" autoplay loop muted playsinline width="100%" style="max-width: 100%; border-radius: 8px;"> |
| 120 | <a href="https://github.com/user-attachments/assets/008911c6-b015-47ff-a286-1d8c22f5817e">下载 / 播放 CLI 演示视频</a> |
| 121 | </video> |
| 122 | </td> |
| 123 | </tr> |
| 124 | </table> |
| 125 | <sub><i>演示：TUI 界面、配色主题切换与信息布局优化</i></sub> |
| 126 | |
| 127 | <p al |
Related
6 picksType
- wikipedia-mcpMCP server for Wikipedia APIMay 2026
- gpt-researcherGPT Researcher is an autonomous agent designed for comprehensive online research on a variety of tasks.Jul 2026
- arxiv-mcp-serverMCP server for accesing arXiv APIAug 2025
- arxiv-mcp-serverA Model Context Protocol server for searching and analyzing arXiv papersJul 2026
- knowledgebase-mcpBioContextAI Knowledgebase MCP server for biomedical agentic AIJan 2026
- mcp-server-serperSerper MCP Server supporting search and webpage scrapingMar 2025
