alchaincyf

Hermes Agent Orange Book — AI skill for Claude Code

AI community

Hermes Agent 从入门到精通 · 橙皮书系列 · Nous Research 开源 AI Agent 框架实战指南.

How to install Hermes Agent Orange Book

This entry records only its repository, not the path inside it, so there is no exact command to give. Open alchaincyf/hermes-agent-orange-book and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Hermes Agent Orange Book does

Hermes Agent 从入门到精通 · 橙皮书系列 · Nous Research 开源 AI Agent 框架实战指南.

Alternatives in AI

Agency Agents Zh — 🎭 211 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 16 种工具，覆盖工程/设计/营销/金融等 18 个部门 6.9k ★
Claude Code Book — 《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 2.8k ★
Iai Personal Memory Engine — A cyber brain for your AI 866 ★

README

**English** | [中文版 README](README_zh.md)

hermes-agent-orange-book Hero Animation
Animated with huashu-design skill

Hermes Agent 2.0: The Complete Guide

橙皮书 (Orange Book) Series · by HuaShu (花叔)

A hands-on guide to [Hermes Agent](https://github.com/NousResearch/hermes-agent), the open-source AI Agent framework by [Nous Research](https://hermes-agent.nousresearch.com/) — the first agent that ships with its "reins" built in, and the reins grow themselves.

**This is a from-scratch rewrite.** The first edition was based on Hermes v0.7.0. Two months and nine releases later, the product had grown a whole new face — a native desktop app, a full browser dashboard, 23 messaging platforms — so the book is rebuilt around v0.16.0 ("The Surface Release").

Download

Version	PDF
中文版 (Chinese)	PDF Download
English	PDF Download

Errata

**The data-collection inference in §03 ("Why Nous Built It") is wrong.** Thanks to [@lishaogang](https://github.com/lishaogang) for pointing this out in [issue #7](https://github.com/alchaincyf/hermes-agent-orange-book/issues/7).

Under "Motive one," the book claims that "Hermes Agent isn't just a product, it's also a massive-scale harvester that collects real-world data for Nous's own models," and draws a chain from "users' real usage → tool-call trajectories → compressed into training data → next-gen models." That chain breaks at its very first link: