The Shell & Email

Is email the best way to work when working with multiple agents at the same time? Each email thread is a session. And it supports group conversations. See what I built on Github.

当同时与多个智能体（Agents）协作时，电子邮件是最好的工作方式吗？每一个邮件主题（Thread）就是一个会话，而且它还支持群组对话。来看看我在 GitHub 上构建的项目。

With email, you’re not chained to a single company’s app or, even, your laptop. You can do it anywhere and email is the most versatile in poor network conditions, on top of that.

使用电子邮件，你不会被束缚在某一家公司的应用程序甚至是你自己的笔记本电脑上。你可以在任何地方工作，此外，在网络状况不佳的情况下，电子邮件也是最通用的工具。

Email already solves the problem for working with people in an asynchronous and distributed way. Large language models get this, like they get the shell.

电子邮件已经解决了以异步和分布式方式与人协作的问题。大型语言模型（LLM）理解这一点，就像它们理解 Shell 一样。

Background / 背景

We like the shell and the terminal that lets us use it. And for practical reasons. The shell composes and enables interoperability with other applications without a gatekeeper. Once you get the hang of it, using the terminal is fun and liberating.

我们喜欢 Shell 以及让我们能够使用它的终端，这出于实际原因。Shell 可以组合并实现与其他应用程序的互操作性，而无需任何“守门人”。一旦你掌握了它，使用终端就会变得既有趣又令人感到自由。

There is no coincidence that LLMs are most useful to us when harnessed to the shell. And if we need to work very closely with an agent, doing so from the terminal is best so we can be as close to the shell as possible.

LLM 在与 Shell 结合时对我们最有用，这绝非巧合。如果我们确实需要与某个智能体紧密协作，在终端中进行操作是最好的，因为这样我们可以尽可能地贴近 Shell。

I’m thankful for that. We mostly use Claude Code, Codex CLI, and others, such as OpenCode that uses the shell and are worked with by us on the terminal (uses the shell). We don’t have to use an iPhone App or some cloud-based web app by a single company to use a computer productively.

对此我心存感激。我们主要使用 Claude Code、Codex CLI 以及其他工具（例如 OpenCode），它们都使用 Shell，并且我们在终端中与它们交互。我们不必为了高效地使用计算机，而去依赖某一家公司的 iPhone App 或云端 Web 应用。

However, there are clearly limitations when you must work with many agents. It’s dizzying. We often need to work asynchronously with agents working on different things. Stop. Do something else. Live life. Check on it a bit. Return to it easily on our own time, etc.

然而，当你必须与许多智能体协作时，局限性显而易见。这让人眼花缭乱。我们经常需要与处理不同任务的智能体进行异步协作：停下来，做点别的事，享受生活，偶尔检查一下进度，然后在我们自己的时间轻松地回到工作中，等等。

Again, email already solves the problem for working with people in an asynchronous and distributed way. That translates well when working with agents, and even other people and agents.

再次强调，电子邮件已经解决了以异步和分布式方式与人协作的问题。这种模式在与智能体协作时同样适用，甚至可以扩展到人与智能体的混合协作中。

How I got here / 我是如何走到这一步的

After the first release of Machtiani over a year ago, I began feeding Machtiani’s answers back into its next instructions. I didn’t release until now to pursue this. An iterative instructions loop that drove a worker that is lightweight supervisor.

在一年多前发布 Machtiani 的第一个版本后，我开始将 Machtiani 的回答反馈到它的下一条指令中。为了实现这一点，我直到现在才发布更新。这是一个迭代的指令循环，驱动着一个轻量级的监督者（Supervisor）。

That lightweight supervisor can work with any agents already installed on your computer.

这个轻量级监督者可以与你电脑上已经安装的任何智能体协同工作。

I found email to be the most natural and liberating way to work with others and agents together.

我发现，电子邮件是与他人及智能体共同协作时，最自然、最自由的方式。

See Machtiani on GitHub.

在 GitHub 上查看 Machtiani。

— David Szigeti