不要构建多智能体

We’ll work our way up to the following principles:

我们将逐步遵循以下原则：

Share context
分享上下文
Actions carry implicit decisions
行动带有隐含的决策

Why think about principles?

为什么要考虑原则？

HTML was introduced in 1993. In 2013, Facebook released React to the world. It is now 2025 and React (and its descendants) dominates the way developers build sites and apps. Why? Because React is not just a scaffold for writing code. It is a philosophy. By using React, you embrace building applications with a pattern of reactivity and modularity, which people now accept to be a standard requirement, but this was not always obvious to early web developers.

HTML于1993年推出。2013年，Facebook向世界发布了React。现在是2025年，React（及其后代）主导了开发者构建网站和应用的方式。为什么？因为React不仅仅是编写代码的框架。它是一种哲学。通过使用React，您接受以反应性和模块化的模式构建应用程序，这现在被人们视为标准要求，但这对早期的网络开发者来说并不总是显而易见。

In the age of LLMs and building AI Agents, it feels like we’re still playing with raw HTML & CSS and figuring out how to fit these together to make a good experience. No single approach to building agents has become the standard yet, besides some of the absolute basics.

在LLM和构建AI代理的时代，感觉我们仍在玩弄原始的HTML和CSS，并试图找出如何将这些结合在一起以创造良好的体验。除了某些绝对基本的内容外，构建代理的单一方法尚未成为标准。

In some cases, libraries such as https://github.com/openai/swarm by OpenAI and https://github.com/microsoft/autogen by Microsoft actively push concepts which I believe to be the wrong way of building agents. Namely, using multi-agent architectures, and I’ll explain why.
在某些情况下，像 https://github.com/openai/swarm 由 OpenAI 和 https://github.com/microsoft/autogen 由 Microsoft 这样的库积极推动我认为是构建代理的错误方式的概念。也就是说，使用多代理架构，我将解释原因。

That said, if you’re new to agent-building, there are lots of resources on how to set up the basic scaffolding [1] [2]. But when it comes to building serious production applications, it's a different story.

也就是说，如果你是代理构建的新手，有很多资源可以帮助你设置基本的框架 [1] [2]。但当涉及到构建严肃的生产应用时，情况就不同了。

A Theory of Building Long-running Agents

构建长时间运行代理的理论

Let’s start with reliability. When agents have to actually be reliable while running for long periods of time and maintain coherent conversations,...