> ## Documentation Index
> Fetch the complete documentation index at: https://se7en.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 课程

> AI Infra 领域的系统性课程

## LLM

| 课程                                                                                                                                                                            | 简介                                                                                                |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- |
| [CSCI 1390, Spring 2025: Systems for Machine Learning](https://cs.brown.edu/courses/csci1390/)                                                                                | 主题包括高效训练和推理、理解如何构建硬件 ML 算法、理解 ML 算法性能、GPU 编程和 CUDA、Transformer 架构、高效检索等                           |
| [CS336: Language Modeling from Scratch (Stanford / Spring 2025)](https://cs336.stanford.edu/spring2025/index.html) <br /> [配套视频](https://www.bilibili.com/video/BV1zvt9zKEK6) | 手把手从零构建一个完整的语言模型——从 tokenizer、Transformer 到分布式训练、数据处理和 RLHF 对齐，5 个实战 assignment 覆盖 LLM 全链路，代码全部开源 |

## Agent

| 课程                                                                    | 简介                                                                                                                |
| --------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------- |
| [Learn Claude Code](https://github.com/shareAI-lab/learn-claude-code) | 从零到一构建一个类 Claude Code 的 AI Agent，12 个渐进式课程，涵盖 Agent Loop、工具调用、子代理、上下文压缩、任务系统、多代理协作、Worktree 隔离等机制                 |
| [从零开始理解 Agent](https://mp.weixin.qq.com/s/Ur3jsyDYobBocXd8ts0gpw)     | 从一个极简开源项目 [nanoAgent](https://github.com/GitHubxsy/nanoAgent) 出发，逐层拆解 OpenClaw / Claude Code 等 AI Agent 背后的全部核心概念 |