--- title: "Cursor 3.7 Moves Your Coding Agent to the Cloud in One Click" subtitle: "Cursor's v3.7 update makes it trivially easy to push agents to the cloud mid-session, spin up parallel subagents with /in-cloud, and set up a reusable dev environment in under 10 minutes." url: "https://alphasignal.ai/news/cursor-3-7-moves-your-coding-agent-to-the-cloud-in-one-click" author: "AlphaSignal Newsroom" author_url: "https://alphasignal.ai/editorial-team" company: "Cursor" company_url: "https://alphasignal.ai/company/cursor_ai" published: "2026-06-17T21:58:40.000Z" updated: "2026-06-17T22:21:43.494Z" type: "News" topics: - "Development" - "Agents" subtopics: - "Code Agents" - "Code Agents" - "Agent Frameworks" - "Tool Use" upvotes: 6225 read_time: "5 min" source_url: "https://cursor.com/changelog/cloud-in-agents-window" comments: 0 --- # Cursor 3.7 Moves Your Coding Agent to the Cloud in One Click > Cursor's v3.7 update makes it trivially easy to push agents to the cloud mid-session, spin up parallel subagents with /in-cloud, and set up a reusable dev environment in under 10 minutes. Cursor just shipped version 3.7, and the headline feature is deceptively simple: moving a coding agent from your laptop to the cloud is now a one-click operation. But underneath that convenience is a meaningful shift in how the tool thinks about where work happens, and how much of it can run without you. ## The local-to-cloud handoff problem Running agents locally has always had a ceiling. Local agents quickly run into conflicts and compete with each other, and with you, for your computer's resources. The more tasks you throw at them, the more your machine slows down. Cursor's answer has been cloud agents for a while now, but the friction of getting there was real. This update removes most of it. The release introduces updates to cloud agents in the Agents Window of the Cursor desktop app, covering three main areas: cloud environment setup, cloud subagents with `/in-cloud`, and more reliable handoff between local and cloud sessions. ![Dropdown showing Local and Cloud agent location options](https://ptht05hbb1ssoooe.public.blob.vercel-storage.com/assets/changelog/handoff-to-cloud.png) ## Spin up a subagent with one slash command The most immediately useful addition is `/in-cloud`. Typing `/in-cloud` spins up a cloud subagent in its own VM to work on the next task you submit. It runs on its own VM and branch, so your local workspace stays clean and responsive. This is not just offloading work, it is a proper isolation primitive. The subagent gets its own branch and environment, completely separate from whatever you are doing locally. It is especially useful for isolating long-running or parallel work like fixing CI, investigating an issue, or exploring a codebase while you keep working locally. There is also a new `/babysit` command for PRs. You can ask a cloud subagent to babysit a PR by clicking on the quick-action pill or using `/babysit`, and the cloud agent will iterate remotely to prepare your PR for merge without tying up the local session. The cloud subagent can run in the background without interrupting the parent agent, which can continue to run locally or in the cloud. ## A dev environment in under 10 minutes The other major piece is cloud environment setup. Previously, getting a cloud agent to actually run your code, install dependencies, and test changes required manual configuration. Now Cursor handles it for you. Cursor can help you set up your dev environment in the cloud in less than 10 minutes. You can watch the agent's progress in a shared terminal session as it handles setup tasks like installing dependencies. The key innovation here is snapshotting. Your environment is captured in a reusable snapshot, so future cloud agents start up faster with the ability to test changes by running your software. It can iterate over long time horizons until outputs are verified. Commit the config to `.cursor/environment.json` and the whole team benefits from the same pre-baked environment on every future agent run. This matters because an agent that cannot run your tests is fundamentally limited. Agents are only as capable as the environments they run in. An agent that can write code but can't run tests, query services, or reach APIs cannot close the loop on its work. The snapshot system is Cursor's answer to that gap. ## What cloud agents can actually do Once in the cloud, agents are not just running text generation. Because they have access to their own virtual machine, cloud agents can build, test, and interact with the changed software. They can also use computers to control the desktop and browser. Cloud agents support MCP servers, giving them access to external tools and data sources like databases, APIs, and third-party services. The practical use cases this unlocks: - Kick off a bug fix from your phone while your laptop is closed, and come back to a PR - Run multiple agents in parallel on different features without resource contention - Let an agent fix a flaky CI pipeline in the background while you work on something else - Have an agent babysit a PR through review cycles without keeping a session open - Set up a shared cloud environment once, and have every team member's agents start from the same snapshot ## Seamless back-and-forth You can move agent sessions more reliably between your local computer and the cloud. You can offload long-running work from your machine and run as many cloud agents in parallel as you want. Pull a cloud agent back down to local to test changes yourself. This bidirectional handoff is what makes the workflow feel natural rather than a one-way ejection to the cloud. For mobile access, you can install Cursor as a Progressive Web App for a native-feeling mobile experience. On iOS, open cursor.com/agents in Safari, tap the share button, then "Add to Home Screen". On Android, open the URL in Chrome, tap the menu, then "Install App". ## Availability and cost The update is live now as part of Cursor version 3.7. All individual plans include unlimited tab completions, extended agent usage limits on all models, access to Bugbot, and access to Cloud Agents. Cloud Agents are charged at API pricing for the selected model. You'll be asked to set a spend limit when you first start using them. You need to be on a paid Cursor plan. The base Pro plan starts at $20 per month, with Pro+ at $60/month recommended for daily agent users. The broader context here is that the central idea behind Cursor 3 is that developers spend more time orchestrating agents than editing code directly, and the tooling should reflect this. This update is the most concrete expression of that bet yet: your machine is just one node in a larger compute graph, and the work should flow wherever it runs best. ## Sources - [X post by @cursor_ai](https://x.com/cursor_ai/status/2067366343817805899) - [Cloud Environment Setup and Cloud Subagents in Agents Window · Cursor Changelog](https://cursor.com/changelog/cloud-in-agents-window) - [Cloud Agents | Cursor Docs](https://cursor.com/docs/cloud-agent) - [Cursor 3 Introduces Agent-First Interface – InfoQ](https://www.infoq.com/news/2026/04/cursor-3-agent-first-interface/) - [Cursor · Pricing](https://cursor.com/pricing) - [Cloud Agents · Cursor Blog](https://cursor.com/blog/cloud-agents)