datawhalechina/hello-agents

hello-agents is a Chinese-language tutorial repository for learning how to build AI agents from the ground up. It is produced by Datawhale, a Chinese open-source education organization, and is structured as a progressive course that takes a learner from basic large language model concepts all the way through building sophisticated multi-agent systems. The curriculum begins with the fundamentals of how large language models work, covering topics like prompt engineering, function calling, and tool use. It then introduces agent architectures, explaining how a model can plan actions, call external tools, observe results, and iterate toward a goal. Later modules cover retrieval-augmented generation so agents can query external knowledge bases, and the course closes with multi-agent coordination patterns where multiple specialized agents collaborate to complete complex tasks. The Model Context Protocol is covered as a way to standardize how agents interact with tools and data sources. You would use this resource if you are a Chinese-speaking developer who wants a structured, beginner-friendly introduction to building AI agents in Python. It is especially useful for students and practitioners who find English-language resources difficult to work with, or for those who want a curated learning path rather than piecing together documentation and blog posts on their own. The course is hands-on, with Python code examples throughout. The entire course is written in Chinese and the code examples use Python. It is maintained as an open-source educational project and welcomes contributions from the community.