datawhalechina/hello-agents

Project overview

Adopt this as a Chinese-language tutorial when your goal is to learn how to build AI Native Agents through theory, hands-on agent paradigms, and multi-agent examples. It is a learning resource rather than documented production deployment guidance.

Project type

AI Agent · RAG

Use cases

Automation · Learning & Education

Deployment

Refer to project documentation

License

License pending

Best for

• Developers, educators, and researchers who can work with Chinese tutorial content and want a practice-oriented introduction to AI Native Agent construction.

Key capabilities

• Provides hands-on implementation material for ReAct, Plan-and-Solve, and Reflection.
• Covers comprehensive multi-agent projects including a smart travel assistant, an automated deep-research agent, and cyber town.
• Provides step-by-step material on context engineering, memory, protocols, and evaluation.
• Covers practical LLM training from SFT to GRPO in an Agentic RL context.

Limitations and risks

• The tutorial content is primarily in Chinese.
• GPU needs, minimum hardware, data boundaries, cost dependencies, telemetry, operating systems, external services, and model requirements are not documented.

Getting started

• The documented first path is to visit the online reading website or download the PDF; this requires no installation for reading.

Evidence and sources

• GitHub project 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
• README: Hello-Agents 是 Datawhale 社区的<strong>系统性智能体学习教程</strong>。
• README: <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>
• README: - 🛠️ <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 - ⚙️ <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 - 🤝 <st…
• Release: Hello-agents V1.0.2 20260210

Reviewed at: 2026-07-17T05:46:20Z