Cloudflare OS: an open platform for agents, apps, and work

Cloudflare OS: an open platform for agents, apps, and work

Cloudflare OS:面向智能体、应用与工作的开放平台

Every organization has a mission, a reason for being. Organizations pass that mission — along with their terminology, procedures, systems, standards, and ways of working — to their people. People, in turn, take this context together with their own experience and work towards the mission. 每个组织都有其使命和存在的理由。组织将这一使命,连同其术语、流程、系统、标准和工作方式,传递给员工。而员工则将这些背景信息与个人经验相结合,为实现使命而努力。

Work can take many forms, from code, to documents and slides, to relationships, to outcomes in the physical world. Some of these are straightforward: code either runs or it doesn’t. Agents have been using this feedback loop to produce code that “works” for developers over the last couple of years. But what about the rest of us? 工作可以采取多种形式,从代码、文档和幻灯片,到人际关系,再到物理世界的成果。其中一些工作非常直观:代码要么能运行,要么不能。过去几年里,智能体(Agents)一直利用这种反馈循环为开发者生成“有效”的代码。但对于我们其他人呢?

Bringing the same leverage to the rest of the organization is a harder problem. Agents need to understand the context of the company and be able to reach the systems people use to do their jobs. They need to turn that context and access into work that moves the organization towards its mission. 将同样的杠杆效应带给组织中的其他人是一个更难的问题。智能体需要理解公司的背景,并能够访问员工日常工作所使用的系统。它们需要将这些背景信息和访问权限转化为推动组织实现使命的工作。

That’s why we created Cloudflare OS. It gives every person an agent and workspace built around their company: how it works, what it knows, and the systems it relies on. 这就是我们创建 Cloudflare OS 的原因。它为每个人提供了一个围绕其公司构建的智能体和工作空间:了解公司如何运作、掌握哪些知识,以及依赖哪些系统。

In May of this year, we gave every person at Cloudflare access to the first version of Cloudflare OS. Thousands of people across every function, many of them outside of engineering, use it every day to create documents and slides, automate repeatable tasks, and build small apps to visualize data and help them do their work. 今年 5 月,我们向 Cloudflare 的每一位员工开放了 Cloudflare OS 的第一个版本。数千名来自各个职能部门的员工(其中许多是非工程人员)每天都在使用它来创建文档和幻灯片、自动化重复性任务,并构建小型应用来可视化数据,从而辅助他们的工作。

Cloudflare OS also gave everyone a shared library of context and skills built by teams at Cloudflare. It captures our terminology, procedures, and best-known ways of doing recurring work as instructions an agent can follow. When one person figures out a better way to do something, everyone else can use it. Cloudflare OS 还为每个人提供了一个由 Cloudflare 各团队构建的共享背景和技能库。它将我们的术语、流程和处理重复性工作的最佳实践记录为智能体可以遵循的指令。当一个人找到更好的工作方法时,其他人都可以直接使用。

Today, we are open sourcing a new version of Cloudflare OS. Any organization can deploy it, connect it to internal systems, and make it their own. 今天,我们开源了新版本的 Cloudflare OS。任何组织都可以部署它,将其连接到内部系统,并打造属于自己的平台。

What we learned from the first version 我们从第一个版本中学到了什么

The Cloudflare OS we are open sourcing today is based on what we learned from running the first version internally, a journey our CIO, Sam Rhea, covers in his blog post. 我们今天开源的 Cloudflare OS 是基于我们在内部运行第一个版本时所获得的经验,我们的首席信息官 Sam Rhea 在他的博客文章中详细介绍了这一历程。

The first version centered on individuals working with agents through private workspaces. Apps were static rather than live software connected to internal systems, and mostly deterministic jobs still required running an agent skill again and consuming more model tokens. 第一个版本侧重于个人通过私有工作空间与智能体协作。当时的应用是静态的,而非连接到内部系统的实时软件;且大多数确定性任务仍需要重复运行智能体技能,从而消耗更多的模型 Token。

Collaboration exposed a more fundamental challenge. Access to an MCP server told us which tools an agent could call, but not which underlying resources the agent had observed. Once people began sharing workspaces, apps, and outputs, we needed to ensure that collaboration could not expose information someone was not permitted to see. 协作揭示了一个更根本的挑战。访问 MCP 服务器告诉我们智能体可以调用哪些工具,但无法告知智能体观察到了哪些底层资源。一旦人们开始共享工作空间、应用和输出结果,我们就必须确保协作不会泄露他人无权查看的信息。

We rebuilt Cloudflare OS on a new foundation to solve these problems. Security had to be part of the platform, not something every person building an app or using an agent has to implement correctly. 我们在新的基础上重建了 Cloudflare OS 以解决这些问题。安全性必须成为平台的一部分,而不是每个构建应用或使用智能体的人都必须自行正确实现的功能。

The result is a platform designed to belong to the company running it. You can customize the interfaces, connect your tools, and add the skills and context that capture how your organization works. 最终的成果是一个旨在归属于运行它的公司的平台。你可以自定义界面、连接工具,并添加能够体现你组织运作方式的技能和背景信息。

Introducing Cloudflare OS Cloudflare OS 简介

Cloudflare OS starts with a conversation in your browser, like many other AI tools. What makes it different is that each conversation is grounded in the context and skills your organization has curated. Give your workspace a goal, and it can draw on that knowledge and work with the tools and data your organization already uses to achieve it. Cloudflare OS 像许多其他 AI 工具一样,始于浏览器中的对话。它的不同之处在于,每一次对话都植根于你组织所策划的背景信息和技能。为你的工作空间设定一个目标,它就能利用这些知识,并与你组织现有的工具和数据协作来实现目标。

Cloudflare OS combines three parts: Cloudflare OS 结合了三个部分:

  • An agent workspace grounded in context and skills your company curates, with an isolated runtime where agents can write and run code. 一个植根于公司策划的背景和技能的智能体工作空间,并配有隔离的运行时环境,智能体可以在其中编写和运行代码。
  • A new security and governance framework for safe access to internal data and services. 一套用于安全访问内部数据和服务的全新安全与治理框架。
  • A platform for personal, modifiable apps that people can build, share, and continue changing. 一个供个人使用、可修改的应用平台,人们可以在此构建、共享并持续改进应用。

What begins as a conversation can become a doc, an app, or a workflow that continues doing the work. 始于对话的内容可以演变成文档、应用或持续执行工作的流程。

An agent workspace for everyone in your company 为公司每个人打造的智能体工作空间

Agent workspaces were designed for everyone in your organization to use. You interact with them in your browser, so you don’t have to be a developer or know how to use a terminal. A workspace combines agent sessions, persistent state, outputs and files, resource access, and an isolated runtime where the agent can write and run code. 智能体工作空间旨在供组织中的每个人使用。你在浏览器中与它们交互,因此无需成为开发者或了解如何使用终端。工作空间结合了智能体会话、持久化状态、输出与文件、资源访问,以及一个智能体可以编写和运行代码的隔离运行时环境。

They come loaded with the curated context and skills your team or company has collected. No more reinventing the wheel for every task — if someone on your team has figured out the best way to do something, everyone benefits. People no longer have to explain the same process, terminology, and best practices to a model every time they start a task. 它们预装了你的团队或公司收集的策划背景和技能。无需再为每项任务重复造轮子——如果团队中有人找到了最佳工作方法,每个人都能从中受益。人们不再需要在每次开始任务时都向模型解释相同的流程、术语和最佳实践。

A few things you can do: 你可以做的一些事情:

  • Research and ask questions: Ask a workspace to research a topic using company context and the resources you make available to it. The agent can write code to search, filter, join, and analyze information instead of pulling an entire dataset into the model’s context window. 研究并提问:要求工作空间利用公司背景和你提供的资源来研究某个主题。智能体可以编写代码来搜索、过滤、合并和分析信息,而不是将整个数据集拉入模型的上下文窗口。
  • Create docs, slides, and spreadsheets: A workspace can turn its research into a document, presentation, or spreadsheet that you can continue editing. These outputs do not have to be static files. They can remain connected to live data, be updated as their sources change, and still be exported to familiar formats or services such as Google Drive. 创建文档、幻灯片和电子表格:工作空间可以将研究成果转化为你可以继续编辑的文档、演示文稿或电子表格。这些输出不必是静态文件。它们可以保持与实时数据的连接,随源数据的变化而更新,并且仍然可以导出为熟悉的格式或服务,例如 Google Drive。
  • Create collaborative, connected apps for your team: When a document or spreadsheet is not enough, the agent can build an app with its own interface, logic, and state. The app can use connected company resources and support multiple people working together. 为团队创建协作式、互联的应用:当文档或电子表格不足以满足需求时,智能体可以构建一个拥有独立界面、逻辑和状态的应用。该应用可以使用已连接的公司资源,并支持多人协作。
  • Run deterministic workflows: Not every job needs a full agent session. Many are a known sequence of steps with one or two places where judgment is useful. A workspace can turn those jobs into mostly deterministic workflows, using code for the predictable steps and a model only where it adds value. Workflows can run on demand, on a schedule, or when an event occurs in a connected system. Cloudflare OS gives agents and apps governed access to systems of record through Gatekeepers. 运行确定性工作流:并非每项工作都需要完整的智能体会话。许多工作是已知的步骤序列,其中只有一两处需要人工判断。工作空间可以将这些工作转化为大部分确定性的工作流,对可预测的步骤使用代码,仅在需要增加价值的地方使用模型。工作流可以按需运行、按计划运行,或在连接的系统中发生事件时触发。Cloudflare OS 通过“守门人”(Gatekeepers)为智能体和应用提供受控的记录系统访问权限。