{"data":{"slug":"datawhalechina-hello-agents","name":"hello-agents","tagline":"Course on building intelligent agents from scratch","github_url":"https://github.com/datawhalechina/hello-agents","owner":"datawhalechina","repo":"hello-agents","owner_avatar_url":"https://avatars.githubusercontent.com/u/46047812?v=4","primary_language":"Python","stars":73126,"forks":9108,"topics":["agent","llm","rag","tutorial"],"archived":false,"github_pushed_at":"2026-08-14T11:23:24+00:00","maintenance_label":"Very active","stars_delta_30d":6436,"url":"https://www.graphcanon.com/tools/datawhalechina-hello-agents","markdown_url":"https://www.graphcanon.com/tools/datawhalechina-hello-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/datawhalechina-hello-agents","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=datawhalechina-hello-agents","description":"📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程","homepage_url":"https://hello-agents.datawhale.cc","license":"Other","open_issues":155,"watchers":210,"ai_summary":"A comprehensive guide and practical tutorial for constructing AI agents, including an introduction to LLMs and RAG methods.","readme_excerpt":"<div align=\"right\">\n  <a href=\"./README_EN.md\">English</a> | 中文\n</div>\n\n<div align='center'>\n  <img src=\"./docs/images/hello-agents.png\" alt=\"alt text\" width=\"100%\">\n  <h1>Hello-Agents</h1>\n  <h3>🤖 《从零开始构建智能体》</h3>\n  <div align=\"center\">\n  <a href=\"https://trendshift.io/repositories/15520\" target=\"_blank\">\n    <img src=\"https://trendshift.io/api/badge/repositories/15520\" alt=\"datawhalechina%2Fhello-agents | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/>\n  </a>\n  </div>\n  <p><em>从基础理论到实际应用，全面掌握智能体系统的设计与实现</em></p>\n  <img src=\"https://img.shields.io/github/stars/datawhalechina/Hello-Agents?style=flat&logo=github\" alt=\"GitHub stars\"/>\n  <img src=\"https://img.shields.io/github/forks/datawhalechina/Hello-Agents?style=flat&logo=github\" alt=\"GitHub forks\"/>\n  <img src=\"https://img.shields.io/badge/language-Chinese-brightgreen?style=flat\" alt=\"Language\"/>\n  <a href=\"https://github.com/datawhalechina/Hello-Agents\"><img src=\"https://img.shields.io/badge/GitHub-Project-blue?style=flat&logo=github\" alt=\"GitHub Project\"></a>\n  <a href=\"https://datawhalechina.github.io/hello-agents/\"><img src=\"https://img.shields.io/badge/在线阅读-Online%20Reading-green?style=flat&logo=gitbook\" alt=\"Online Reading\"></a>\n</div>\n\n---\n\n## 🎯 项目介绍\n\n&emsp;&emsp;如果说 2024 年是\"百模大战\"的元年，那么 2025 年无疑开启了\"Agent 元年\"。技术的焦点正从训练更大的基础模型，转向构建更聪明的智能体应用。然而，当前系统性、重实践的教程却极度匮乏。为此，我们发起了 Hello-Agents 项目，希望能为社区提供一本从零开始、理论与实战并重的智能体系统构建指南。\n\n&emsp;&emsp;Hello-Agents 是 Datawhale 社区的<strong>系统性智能体学习教程</strong>。如今 Agent 构建主要分为两派，一派是 Dify，Coze，n8n 这类软件工程类 Agent，其本质是流程驱动的软件开发，LLM 作为数据处理的后端；另一派则是 AI 原生的 Agent，即真正以 AI 驱动的 Agent。本教程旨在带领大家深入理解并构建后者——真正的 AI Native Agent。教程将带领你穿透框架表象，从智能体的核心原理出发，深入其核心架构，理解其经典范式，并最终亲手构建起属于自己的多智能体应用。我们相信，最好的学习方式就是动手实践。希望这本教程能成为你探索智能体世界的起点，能够从一名大语言模型的\"使用者\"，蜕变为一名智能体系统的\"构建者\"。\n\n## 📚 快速开始\n\n### 在线阅读\n**[🌐 国外访问](https://datawhalechina.github.io/hello-agents/)** | **[🚀 国内加速](https://hello-agents.datawhale.cc)** - 无需下载，随时随地学习\n\n### 本地阅读\n如果您希望在本地阅读或贡献内容，请参考下方的学习指南。\n\n### ✨ 你将收获什么？\n\n- 📖 <strong>Datawhale 开源免费</strong> 完全免费学习本项目所有内容，与社区共同成长\n- 🔍 <strong>理解核心原理</strong> 深入理解智能体的概念、历史与经典范式\n- 🏗️ <strong>亲手实现</strong> 掌握热门低代码平台和智能体代码框架的使用\n- 🛠️ <strong>自研框架 [HelloAgents](https://github.com/jjyaoao/helloagents)</strong> 基于 Openai 原生 API 从零构建一个自己的智能体框架\n- ⚙️ <strong>掌握高级技能</strong> 一步步实现上下文工程、Memory、协议、评估等系统性技术\n- 🤝 <strong>模型训练</strong> 掌握 Agentic RL，从 SFT 到 GRPO 的全流程实战训练 LLM\n- 🚀 <strong>驱动真实案例</strong> 实战开发智能旅行助手、赛博小镇等综合项目\n- 📖 <strong>求职面试</strong> 学习智能体求职相关面试问题\n\n## 📖 内容导航\n\n| 章节                                                                                        | 关键内容                                      | 状态 |\n| ------------------------------------------------------------------------------------------- | --------------------------------------------- | ---- |\n| [前言](./docs/前言.md)                                                                      | 项目的缘起、背景及读者建议                    | ✅    |\n| <strong>第一部分：智能体与语言模型基础</strong>                                             |                                               |      |\n| [第一章 初识智能体](./docs/chapter1/第一章%20初识智能体.md)                                 | 智能体定义、类型、范式与应用                  | ✅    |\n| [第二章 智能体发展史](./docs/chapter2/第二章%20智能体发展史.md)                             | 从符号主义到 LLM 驱动的智能体演进             | ✅    |\n| [第三章 大语言模型基础](./docs/chapter3/第三章%20大语言模型基础.md)                         | Transformer、提示、主流 LLM 及其局限          | ✅    |\n| <strong>第二部分：构建你的大语言模型智能体</strong>                                         |                                               |      |\n| [第四章 智能体经典范式构建](./docs/chapter4/第四章%20智能体经典范式构建.md)                 | 手把手实现 ReAct、Plan-and-Solve、Reflection  | ✅    |\n| [第五章 基于低代码平台的智能体搭建](./docs/chapter5/第五章%20基于低代码平台的智能体搭建.md) | 了解 Coze、Dify、n8n 等低代码智能体平台使用   | ✅    |\n| [第六章 框架开发实践](./docs/chapter6/第六章%20框架开发实践.md)                             | AutoGen、AgentScope、LangGraph 等主流框架应用 | ✅    |\n| [第七章 构建你的Agent框架](./docs/chapter7/第七章%20构建你的Agent框架.md)                   | 从 0 开始构建智能体框架","github_created_at":"2025-09-07T09:50:24+00:00","created_at":"2026-07-07T17:30:54.222344+00:00","updated_at":"2026-08-16T06:01:55.9106+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"llm","name":"llm"},{"slug":"rag","name":"rag"},{"slug":"tutorial","name":"tutorial"}],"trust":{"provenance":{"is_fork":false,"github_id":1052050442,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-16T06:01:55.185Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":1,"last_release_at":"2026-07-17T09:29:47Z","stars_delta_30d":6436,"open_issues_delta_30d":8},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:56:32.538Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-16T06:01:55.625Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-16T06:01:55.625Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-16T06:01:55.625Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Python knowledge assumed"],"min_ram_gb":4,"requires_docker":false},"constraints":{"min_ram_gb":4,"requires_docker":false},"when_to_use":["You should use hello-agents if you are interested in practical, step-by-step instructions on building intelligent agents from the ground up.","Select hello-agents if your goal is to deepen your understanding of both foundational concepts and advanced techniques like LLMs and Retrieval-Augmented Generation (RAG), which it uniquely emphasizes."],"when_not_to_use":["Avoid using hello-agents if you are looking for a quick, superficial introduction to AI agents; this tool focuses heavily on in-depth learning and practical application.","Do not opt for hello-agents if you want a more general AI development resource; unlike some competitors, it has a narrower focus specifically on agent creation with advanced methods like LLMs and RAG."],"source":"enrich:decision_facts","observed_at":"2026-07-11T12:12:15.785Z"},"constraint_facets":{"min_ram_gb":4,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Min 4 GB RAM; Python knowledge assumed"},{"label":"Adopt for","value":"hello-agents is a comprehensive guide and hands-on tutorial for developing AI agents using LLMs (Large Language Models) and RAG methods."},{"label":"License detail","value":"hello-agents is covered under an unconventional license which may require further review before usage."}]}}