Guillermo Rauch 介绍智能体三部分架构与 Vercel Drives
Muse、Instinct、OpenClaw、Claude Code… 所有成功的智能体都有 3 个关键组件：
🧠 大脑 → 模型、框架（逻辑） 👐 双手 → 工具、计算机、浏览器 🗃️ 文件 → 记忆、技能、仓库
“简单”的方式是将所有这些扔到一个有状态的计算机中（比如 Mac Mini）
比如，你在 Mac 上运行 𝚌𝚕𝚊𝚞𝚍𝚎 或 𝚏𝚡，用 𝚌𝚊𝚏𝚏𝚎𝚒𝚗𝚊𝚝𝚎 让它全天运行，它有存储空间，并安装了 CLI 和应用。
但如果你想在云端以成本效益高的方式运行智能体，你实际上需要将这些部分拆分开来。
🧠 框架可以在 Fluid compute 中运行。为了让它在重启、部署、崩溃时保持可靠，你可以使用 Workflow 使事件日志持久化。
👐 双手可以是一个专用的浏览器集群，比如 Browserbase/Kernel，一个像 Sandbox 这样的计算机，甚至更高效的轻量级工具，比如 just-bash。
🗃️ 🆕 缺失的是一套解耦存储的方法。想象一下，你想每晚运行一个记忆整合定时任务（“做梦”）。你可以直接读写文件，而无需“启动”智能体的完整计算机。
今天我们推出 Sandbox 的完美伴侣：Drives。我们已经为智能体提供了计算机，现在我们为你提供可以随意附加的“外部磁盘”。这还处于早期阶段，我们将很快扩展这里的功能。
顺便说一句，将智能体拆分成这些独立部分不仅能大幅优化成本，还能极大提升安全性和可审计性。我认为否则你甚至无法运行一个安全的智能体！
对照原文
Muse, Instinct, OpenClaw, Claude Code… All successful agents have 3 key components: 🧠 Brain → model, harness (logic) 👐 Hands → tools, computer, browser 🗃️ Files → memories, skills, repos The 'easy' way is to throw all these in 1 stateful computer (a Mac Mini) Like, you run 𝚌𝚕𝚊𝚞𝚍𝚎 or 𝚏𝚡 in your mac, you keep it running all day with 𝚌𝚊𝚏𝚏𝚎𝚒𝚗𝚊𝚝𝚎, it has storage, and CLIs and apps installed. But if you want to cost-efficiently run agents in the cloud, you actually start breaking down these parts. 🧠 The harness can run in Fluid compute. To make it reliable across restarts, rollouts, crashes, you make its event log durable using Workflow. 👐 The hands can be a dedicated browser fleet like Browserbase/Kernel, a computer like Sandbox, and even more efficient lightweight tools like just-bash. 🗃️ 🆕 What was missing was a way to also decouple storage. Imagine you want to run a memory consolidation cron job every night ("dreaming"). You can read/write to the files directly without 'booting up' the agent's full computer. Today we're introducing the perfect companion to Sandbox: Drives. We shipped the computer for agents, now we're giving you the 'external disk' you can attach at will. It's early, and we'll be expanding capabilities here quickly. Btw, breaking apart the agent into these independent parts not only optimizes costs in a big way, it also *massively* improves security and auditability. I'd argue you can't even run a secure agent otherwise!