nexu-io/harness-engineering-guide 是从 https://github.com/nexu-io/harness-engineering-guide. 导入的特工技能候选
概览
nexu-io/harness-engineering-guide 是从 https://github.com/nexu-io/harness-engineering-guide. 导入的特工技能候选
概述（AI 翻译）
构建AI代理工具的实用指南——配有真实代码示例，您可以复制并运行。
🌐 harness-guide.com |中文站
英文 |中文
harness 是运行时包装器，将裸语言模型转变为agent——一个能够感知环境、做出决策并在多步中采取行动的自主系统。该框架处理模型自身无法完成的所有事务：执行工具、内存管理、构建上下文以及执行安全边界。
本指南涵盖了从基础原理到生产模式的线束工程，每篇文章中都有真实代码。
开始
| 主题 | 描述 |
|---|---|
| 什么是线束？ | 3分钟内讲解概念。如何将模型转化为代理。线束、框架与运行时。 |
| 你的第一个线束 | 用50行Python构建一个可用的线束。你可以复制并运行的完整代码。 |
| 框架 vs. 框架 | 何时使用原始框架 vs. LangChain/CrewAI。决策树 + 并排代码比较。 |
核心概念
| 主题 | 描述 |
|---|---|
| 能动循环 | 思考→行为→观察循环。 |
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
The practical guide to building AI agent harnesses — with real code examples you can copy and run.
🌐 harness-guide.com | 中文站
English | 中文
A harness is the runtime wrapper that turns a bare language model into an agent — an autonomous system that can perceive its environment, make decisions, and take actions over multiple steps. The harness handles everything the model can’t do on its own: executing tools, managing memory, assembling context, and enforcing safety boundaries.
This guide covers harness engineering from first principles to production patterns, with real code in every article.
Getting Started
| Topic | Description |
|---|---|
| What is a Harness? | The concept in 3 minutes. How it turns a model into an agent. Harness vs. framework vs. runtime. |
| Your First Harness | Build a working harness in 50 lines of Python. Complete code you can copy and run. |
| Harness vs. Framework | When to use a raw harness vs. LangChain/CrewAI. Decision tree + side-by-side code comparison. |
Core Concepts
| Topic | Description |
|---|---|
| Agentic Loop | The think → act → observe cycle. Turn budgets, parallel tool calls, loop detection, streaming. |
| Tool System | Tool registry, static vs. dynamic loading, MCP protocol, description quality patterns. |
| Memory & Context | Context assembly, session management, two-tier memory (daily logs + long-term). AGENTS.md and MEMORY.md patterns. |
| Guardrails | Permission models, trust boundaries, sandboxing, prompt injection defense. |
Practice
| Topic | Description |
|---|---|
| Context Engineering | Priority-based assembly, three lines of defense for compression, token budgeting. |
| Sandbox | Docker and Firecracker setups, network isolation, filesystem restrictions. |
| Skill System | Skill packaging, on-demand loading, SKILL.md format, thin harness + thick skills. |
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add nexu-io/harness-engineering-guide