通用多格式输入 → 结构化研究报告的 AI 流水线
$git clone https://github.com/gaotiexinqu/oneresearchclawInstalls into the current project.
Install oneresearchclaw by running `git clone https://github.com/gaotiexinqu/oneresearchclaw`, then use it for the current task and follow its documentation at https://github.com/gaotiexinqu/oneresearchclaw.
| 1 | <p align="center"> |
| 2 | <img src="docs/assets/logo.png" alt="OneResearchClaw Header" width="95%"> |
| 3 | </p> |
| 4 | |
| 5 | |
| 6 | <h2 align="center"><b>Start Any Research in One Claw. 🦞</b></h2> |
| 7 | |
| 8 | <p align="center"> |
| 9 | <strong>From real materials to reports with a fully autonomous & skill-driven researcher.</strong> |
| 10 | </p> |
| 11 | |
| 12 | --- |
| 13 | |
| 14 | <p align="center"> |
| 15 | <img src="docs/assets/framework-v6.png" alt="OneResearchClaw Framework" width="100%"> |
| 16 | </p> |
| 17 | |
| 18 | |
| 19 | OneResearchClaw is a **multi-format input → research report generation pipeline** designed for real-world workflows. |
| 20 | It supports starting from meeting audio/video, documents, tables, PPT files, ZIP mixed-material packages, and arXiv / YouTube / Bilibili links, then progressively completes content grounding, literature research, quality review, skill evolution, and multi-format export. |
| 21 | |
| 22 | <p align="center"> |
| 23 | <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="MIT License"></a> |
| 24 | <a href="https://python.org"><img src="https://img.shields.io/badge/Python-3.10%2B-3776AB?logo=python&logoColor=white" alt="Python 3.10+"></a> |
| 25 | <a href="https://github.com/gaotiexinqu/OneResearchClaw"><img src="https://img.shields.io/badge/GitHub-OneResearchClaw-181717?logo=github" alt="GitHub"></a> |
| 26 | <a href="https://github.com/gaotiexinqu/OneResearchClaw#-citation"><img src="https://img.shields.io/badge/Cite-OneResearchClaw-orange?logo=readme&logoColor=white" alt="Citation"></a> |
| 27 | <a href="https://github.com/gaotiexinqu/OneResearchClaw#-star-history"><img src="https://img.shields.io/badge/Star_History-⭐-blue?logo=github" alt="⭐ Star History"></a> |
| 28 | </p> |
| 29 | |
| 30 | <p align="center"> |
| 31 | <a href="./README_CH.md"><b>🌐 中文 README</b></a> · |
| 32 | <a href="https://weiyang209.github.io/OneResearchClaw/"><b>🖥️ Project Page</b></a> · |
| 33 | <a href="#-showcase"><b>🎬 Showcase</b></a> · |
| 34 | <a href="#-quick-start"><b>🚀 Quick Start</b></a> · |
| 35 | <a href="#-skills-catalog"><b>🧩 Skills Catalog</b></a> |
| 36 | </p> |
| 37 | |
| 38 | <p align="center"> |
| 39 | <a href="./docs/assets/wechat.jpg"><b>💬 WeChat</b></a> · |
| 40 | <a href="./docs/assets/rednote.jpg"><b>📕 RedNote</b></a> · |
| 41 | <a href="https://discord.gg/D53kdpX9"><b>🤖 Discord</b></a> |
| 42 | </p> |
| 43 | |
| 44 | |
| 45 | --- |
| 46 | |
| 47 | ## 🎬 Showcase |
| 48 | |
| 49 | <table> |
| 50 | <tr> |
| 51 | <td width="180" align="center"> |
| 52 | <img src="docs/assets/showcase-cover.png" alt="OneResearchClaw Showcase" width="140"> |
| 53 | </td> |
| 54 | <td> |
| 55 | <h3>Generated Report Showcase</h3> |
| 56 | <p> |
| 57 | 5 representative cases across meetings, documents, mixed archives, links, and review workflows — |
| 58 | showing <b>multi-topic splitting</b>, <b>controllable research depth</b>, |
| 59 | <b>review-rewrite improvement</b>, and <b>multi-format delivery</b>. |
| 60 | </p> |
| 61 | <p> |
| 62 | <a href="docs/showcase/SHOWCASE.md"><img alt="View Full Showcase" src="https://img.shields.io/badge/View%20Full%20Showcase-%E2%86%92-3b82f6?style=for-the-badge"></a> |
| 63 | <a href="docs/showcase/SHOWCASE.md#case-overview"><img alt="All Cases" src="https://img.shields.io/badge/All%205%20Cases-ef4444?style=for-the-badge"></a> |
| 64 | </p> |
| 65 | </td> |
| 66 | </tr> |
| 67 | </table> |
| 68 | |
| 69 | |
| 70 | --- |
| 71 | |
| 72 | ## 🔥 News |
| 73 | |
| 74 | - **[2026/04/21] Skill-Evolve is officially released**: OneResearchClaw now supports continuous skill-set evolution based on user feedback, saving personalized preferences as selectable derived versions so the automation pipeline can gradually adapt to the way you work. |
| 75 | |
| 76 | - **[2026/04/20] One-click cloud link ingestion**: Whether the input is an arXiv paper, a YouTube video, or Bilibili content, simply paste the link and the system will automatically download it locally and start the research workflow. |
| 77 | |
| 78 | - **[2026/04/19] Multi-model Review mechanism**: The Review → Rewrite loop supports bounded iterative revision, significantly improving the quality of final deliverables. |
| 79 | |
| 80 | - **[2026/04/17] Controllable Research depth**: Choose from `simple / medium / complex`. Whether you need a quick first pass or a deeper research run, the depth and resource usage are easier to control. |
| 81 | |
| 82 | - **[2026/04/16] Multi-topic parallel execution**: The system can automa |