AI agent harness engineering / education
An open-source Chinese textbook/tutorial that teaches building a Pi-style coding agent from scratch through 15 executable checkpoints in TypeScript.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose for a Claude Code–specific deep dive with a similar chapter-by-chapter harness build if you want that flavor instead of Pi.
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：
Choose for a leaner TypeScript harness-engineering tutorial from 0 to 1 when you want a shorter path than the 15-checkpoint textbook.
Harness engineering beginner tutorial, from 0 to 1
Choose if you prefer Python and a minimal nano harness built from 0 to 1 instead of TypeScript checkpoints.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose when you need broad AI-agent design principles and engineering practice with per-chapter code rather than one focused harness build.
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
Choose when you want a survey of many agentic architectures and a benchmark rather than a single step-by-step implementation.
35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.
Choose when your focus is LangGraph/RAG application recipes and interview prep rather than building a harness from scratch.
https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成