Cursor 推出自托管机器功能，支持云 Agent 在自有基础设施运行
Sep 2, 2026·productRun cloud agents on machines you manageJack Pertschuk6mJack Pertschuk·6m
企业级 AI 应用落地的关键拼图，解决了 Agent 运行在私有网络的安全与合规痛点，有具体架构和集成方案，值得关注。
Blog / product
博客 / 产品
Cursor cloud agents can execute on dynamically scheduled pools of machines inside your network. You manage the underlying infrastructure, while agents are still started and managed from Cursor.
Cursor 云代理可以在您网络内部动态调度的机器池中执行。您管理底层基础设施，而代理仍由 Cursor 启动和管理。
This gives teams more control over where agents execute and what infrastructure they use. Agents can work next to internal services and source control, run on custom hardware, or use operating systems and build pipelines that are difficult to package as a Cloud Agent build.
这使团队对代理的执行位置及其使用的基础设施拥有更多控制权。代理可以与内部服务和源代码控制协同工作，在定制硬件上运行，或使用难以打包为 Cloud Agent 构建的操作系统和构建流水线。
Cloud agents now create more than 60% of the pull requests we merge internally and are taking on a growing share of software work at many of the largest enterprises we work with. As their role expands, the machines they run on matter more too. These new capabilities make it practical for teams to provide and manage that infrastructure at scale.
Cloud Agents 现在创建了我们内部合并的超过 60% 的拉取请求，并在许多与我们合作的最大企业中承担了越来越多的软件开发工作。随着其角色的扩展，它们运行的机器也变得越来越重要。这些新功能使得团队能够大规模地提供和管理该基础设施变得切实可行。
With Lambda MicroVMs as the compute layer for Cursor Cloud Agents, developers can run AI-powered coding agents in their own AWS account. Each machine launches near-instantly from a snapshot, suspends when idle, and resumes with full state. Your coding agents benefit from Lambda's fast startup, strong isolation, and zero fleet management, while Cursor orchestrates the work.
以 Lambda MicroVMs 作为 Cursor Cloud Agents 的计算层，开发者可以在自己的 AWS 账户中运行 AI 驱动的编码代理。每台机器从快照近乎即时启动，空闲时挂起，并保留完整状态恢复运行。您的编码代理受益于 Lambda 的快速启动、强大的隔离性和零集群管理，而 Cursor 则负责编排工作。
Ayush Kulkarni
Ayush Kulkarni
Senior Product Manager, AWS Lambda
AWS Lambda 高级产品经理
#Control where agents execute
#控制代理的执行位置
Cursor-hosted environments remain the default for cloud agents. Each session runs on a dedicated VM inside the Cursor cloud, with its dependencies installed and its own network controls. Per-agent isolation, secret redaction, egress controls, and signed commits meet the security requirements of most teams.
托管在 Cursor 上的环境仍然是云代理的默认设置。每个会话都在 Cursor 云内的专用 VM 上运行，已安装其依赖项并具有独立的网络控制。每个代理的隔离性、密钥脱敏、出口控制和签名提交满足了大多数团队的安全要求。
Teams generally use Self-Hosted Machines when:
团队通常在以下情况下使用自托管机器：
- Agent tool execution needs to happen inside their network, with direct access to source control, internal services, and code repositories.
- Agents require custom hardware, such as GPUs or Macs for iOS development, or infrastructure such as Kubernetes, sandboxes, or managed VMs.
- Their operating system or build pipeline is difficult to package as a Cloud Agent build.
- 代理工具执行需要在他们的网络内部进行，直接访问源代码控制、内部服务和代码仓库。
- 代理需要定制硬件（例如用于 iOS 开发的 GPU 或 Mac），或者需要 Kubernetes、沙箱或托管 VM 等基础设施。
- 其操作系统或构建流水线难以打包为 Cloud Agent 构建。
With Self-Hosted Machines, only the execution environment moves while the agent loop, inference, and planning remain in the Cursor cloud. Tool outputs flow back to Cursor for inference and may contain code, and agent transcripts may be processed and stored by Cursor. Teams can continue to access cloud agents from the desktop app, cursor.com, mobile, Slack, GitHub, and Linear.
使用自托管机器时，只有执行环境发生移动，而代理循环、推理和规划仍保留在 Cursor 云中。工具输出流回 Cursor 用于推理，可能包含代码，代理转录记录可能会由 Cursor 处理并存储。团队可以继续从桌面应用、cursor.com、移动端、Slack、GitHub 和 Linear 访问云代理。
#Workers connect your infrastructure to the Cursor agent loop
#工作节点将您的基础设施连接到 Cursor 代理循环
With Self-Hosted Machines, tool execution moves from a Cursor-hosted VM to a machine in your environment. That machine holds the working copy of the repository, edits files, and runs commands. A worker connects it to the rest of the agent system.
使用自托管机器时，工具执行从 Cursor 托管的虚拟机转移到你环境中的机器上。该机器持有仓库的工作副本，编辑文件并运行命令。一个工作器将其连接到代理系统的其余部分。
To register a machine, run a worker by installing the Cursor CLI and running agent worker start. This opens a long-lived outbound HTTPS connection to the Cursor cloud. When a session begins, Cursor's agent harness handles inference and planning, then sends tool calls to a dedicated worker for execution. The worker returns the results for the next round of inference. Cursor never initiates a connection into your network.
要注册机器，请通过安装 Cursor CLI 并运行 agent worker start 来启动工作器。这将建立与 Cursor 云的长期出站 HTTPS 连接。当会话开始时，Cursor 的代理框架处理推理和规划，然后将工具调用发送给专用工作器以执行。工作器返回结果以供下一轮推理使用。Cursor 永远不会主动发起进入你网络的连接。
Workers can be configured in two ways.
工作器可以通过两种方式配置。
- My Machines. This configuration connects a single laptop or VM to your account and is best suited to personal workflows.
- Pools. A pool is a named queue of workers that can serve a team or enterprise. Capacity increases as requests arrive and decreases after workers disconnect, letting your existing cloud infrastructure scale with developer demand.
- 我的机器（My Machines）。此配置将单个笔记本电脑或虚拟机连接到你的账户，最适合个人工作流。
- 池（Pools）。池是一个命名的工作器队列，可为团队或企业提供服务。随着请求到达容量增加，在工作器断开连接后容量减少，使现有的云基础设施能够随开发人员需求进行扩展。
Developers should have the flexibility to run coding agents on the platform that best supports their workflow, and companies should not have to compromise on control of where agents run and what they can access. The future of development will be built on powerful agents, running in secure, isolated environments.
开发人员应拥有在最能支持其工作流的平台上运行编码代理的灵活性，而公司不应不得不在控制代理运行位置及其访问权限方面做出妥协。开发的未来将建立在强大且运行在安全、隔离环境中的代理之上。
Meagan Gamache
Meagan Gamache
Director of Product Management, Developer Platforms, Cloudflare
Cloudflare 开发者平台产品管理总监
#Cloud agents adapt to your infrastructure
#云代理适应你的基础设施
Worker pools can now scale in response to queued requests and serve work from any repository. We have also added support for several sandbox providers and computer use on Linux alongside Mac.
工作器池现在可以根据排队请求进行扩展，并为任何仓库提供服务。我们还添加了对多种沙箱提供商的支持，并在 Linux 上与 Mac 一起支持计算机使用功能。
#Pools scale with demand and serve any repository
#池随需求扩展并服务于任何仓库
Demand for cloud agents often arrives in bursts and Self-Hosted Machines pools adjust to those bursts automatically. This happens through a controller which watches the request queue and uses a spawn script supplied by the team to start machines as needed.
对云代理的需求通常以突发形式出现，自托管机器池会自动适应这些突发。这是通过一个控制器实现的，该控制器监视请求队列，并使用团队提供的启动脚本按需启动机器。
If a pool has an available worker, that worker claims the request. Otherwise, the request waits until more capacity becomes available, so teams do not have to decide how many machines to leave running.
如果池中有可用的工作器，该工作器将认领请求。否则，请求将等待直到有更多容量可用，因此团队不必决定要保留多少台正在运行的机器。
Teams can set an idle timeout for each worker connection. Once it expires, the machine can reset and re-enter the pool. Teams can also preserve its workspace in case the agent receives a follow-up.
团队可以为每个工作器连接设置空闲超时时间。一旦过期，机器可以重置并重新进入池中。团队还可以保留其工作区，以防代理收到后续任务。
Self-Hosted Machines put teams in control of where Cursor agents run, and Vercel Sandbox makes it effortless. Every task gets an isolated sandbox on demand, no fleet to manage, and nothing sitting idle.
自托管机器让团队掌控 Cursor 代理的运行位置，而 Vercel Sandbox 使其变得毫不费力。每个任务都会按需获得一个隔离的沙箱，无需管理集群，也没有闲置资源。
Allen Zhou
Allen Zhou
Member of Technical Staff, Vercel
Vercel 技术团队成员
Leaving a machine running while its agent is idle can be expensive. But if the machine is released, the agent may need several minutes to reconstruct its workspace when a follow-up arrives. With hibernation, teams can snapshot and stop an idle machine instead. If a follow-up arrives within the reconnect window, the snapshot is restored and a worker starts with the same ID. Otherwise, the request can move to a new machine.
当代理处于空闲状态时保持机器运行可能会产生高昂费用。但如果释放了机器，当后续请求到达时，代理可能需要几分钟来重建工作区。通过休眠功能，团队可以快照并停止空闲机器。如果在重连窗口期内收到后续请求，将恢复快照并由具有相同 ID 的工作器启动。否则，请求可以转移到新机器上。
Pools are not tied to individual repositories. A request only needs to identify the pool, and any available worker can claim it. This lets one pool serve many repositories.
池不与单个存储库绑定。请求只需标识池，任何可用的工作器都可以认领它。这使得一个池可以为多个存储库提供服务。
#Workers run across supported sandbox providers
#工作器在支持沙箱提供商之间运行
Self-Hosted Machines does not require building a custom sandbox layer from scratch. We partner with AWS Lambda, Cloudflare, Coder, Daytona, E2B, Modal, Namespace, and Vercel, allowing workers to be started and orchestrated wherever a team's sandboxes already run.
自托管机器不需要从零开始构建自定义沙箱层。我们与 AWS Lambda、Cloudflare、Coder、Daytona、E2B、Modal、Namespace 和 Vercel 合作，允许在工作器所在团队的沙箱运行的任何地方启动和编排工作器。
Cursor Self-Hosted Machines on Modal gives each Cloud Agent session a Modal Sandbox, so you can hand it a machine tailor-made for its task.
Modal 上的 Cursor 自托管机器为每个 Cloud Agent 会话提供 Modal Sandbox，因此您可以为其提供量身定制的机器。
Adam Azzam
Adam Azzam
Member of Product Staff, Modal
Modal 产品团队成员
#Agents control browsers on Linux and Mac
#代理控制 Linux 和 Mac 上的浏览器
Linux workers now support computer use alongside Macs. With the required computer use dependencies installed, including Chrome or Chromium, an agent can click, take screenshots, and control the browser. You can watch its desktop or take control directly from Cursor.
Linux 工作器现在支持与 Mac 一起使用计算机功能。安装所需的计算机使用依赖项（包括 Chrome 或 Chromium）后，代理可以点击、截图和控制浏览器。您可以观看其桌面或直接通过 Cursor 接管控制权。
You can't build iOS or macOS apps without a Mac. Namespace Devboxes spin up a real Mac for each Cursor Cloud Agent, which can now perform that work on Apple silicon.
没有 Mac 就无法构建 iOS 或 macOS 应用。Namespace Devboxes 为每个 Cursor Cloud Agent 启动一台真实的 Mac，现在可以在 Apple Silicon 上执行该工作。
Hugo Santos
Hugo Santos
CEO, Namespace
Namespace CEO
#Bring cloud agents into your environment
#将云代理引入您的环境
Teams have spent years shaping their infrastructure around how they build software. Self-Hosted Machines lets cloud agents fit more naturally into it, and we're excited to see how far teams take them.
团队多年来一直在围绕他们构建软件的方式来塑造基础设施。自托管机器让云代理更自然地融入其中，我们很高兴看到团队将它们推向多远。
To connect a machine or configure a pool, get started in the docs.
要连接机器或配置池，请参阅文档入门指南。
Related posts
相关文章
Mar 25, 2026·Product
2026年3月25日·产品
Run cloud agents in your own infrastructure
在您自己的基础设施中运行云代理
Katia Bazzi · 4 min read
Katia Bazzi · 4分钟阅读
Aug 13, 2026·Product
2026年8月13日·产品
Cloud agents start 3x faster with builds
借助构建，云代理启动速度提升3倍
Cursor Team · 4 min read
Cursor 团队 · 4 分钟阅读
Feb 24, 2026·Product
2026年2月24日·产品
Cursor agents can now control their own computers
Cursor 智能体现在可以控制自己的电脑
Jonas & Alexi · 10 min read
Jonas & Alexi · 10 分钟阅读
View more posts →
查看更多文章 →
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力