# Cursor Features and Practical Usage ☁️ While your machine sleeps, multiple cloud agents work in parallel on separate branches and hand you back review-ready PRs. Cloud Agents free the agent from the "one laptop" constraint. 🏷️ Title: Cloud Agents 🔗 URL: 📘 Overview Cloud Agents are autonomous agents that run in isolated virtual machines rather than locally. You can run many of them at once on dedicated cloud infrastructure and keep work going without keeping your own machine online. Each agent gets a complete development environment in its own VM. ⚙️ How It Works ・Parallel and independent: launch multiple agents simultaneously, each in its own VM, free of local constraints ・Isolated branches: clone the repo from GitHub, GitLab, Azure DevOps Services, or Bitbucket Cloud, work on a separate branch, and push changes as a PR, keeping work isolated until review ・Verifiable: agents receive full context on your codebase and organization so they can run tests and query services to verify their work ・PRs with artifacts: produce merge-ready PRs with screenshots, videos, and logs. You can even remote-control the agent's desktop to test without checking out the branch locally ・Multi-repo: make coordinated changes across separate frontend, backend, infrastructure, or shared-library repositories Agents reach external tools, databases, and APIs via MCP servers, and repository hooks from `.cursor/hooks.json` run too (excluding IDE-specific and user-level hooks). 🛠️ Practical Usage There are many launch paths: Cursor Web ( the Desktop agent dropdown set to `Cloud`, `@cursor` from Slack/GitHub/Linear, the API, the native iOS app, and an Android PWA. The single most important step for effectiveness is configuring `.cursor/environment.json`, which replicates a full dev environment including the cloned repo, dependencies, secrets, startup commands, and network access. You can set it up via agent-led automatic init, saved snapshots, or a Dockerfile. 💡 Use Cases In the morning, fan out several tasks to the cloud ("investigate this bug and open a fix PR"), and by midday you have a queue of review-ready PRs. Because agents run tests and query APIs autonomously, humans can focus on review. ⚠️ Caveats Agents need read-write access to your repo and dependent repos/submodules, and a paid plan is required. Manage secrets via the Secrets tab in the dashboard rather than `.env.local`. User-level `~/.cursor/hooks.json` is unavailable to cloud VMs. Pricing is standard API billing for the selected model, and you set a spend limit before first use. You can select the context window size for supported models, and a larger window increases token usage and cost. Supported source control providers are GitHub, GitLab, Azure DevOps Services, and Bitbucket Cloud. #Cursor# #CloudAgents#

Launching a new Codex Cloud, much improved from last year. With configurable cloud environments, it’s impossible to go back to building on your laptop once you’ve taken the time to configure it. Agents API, the same tech powering all our cloud agents, including dots, is also now in preview and supports computer use. It allows you to build the same incredible products we are making available today.

Cursor just made Cloud Agents much easier to start with You no longer need a GitHub repo or third-party source control before you start building Just hit “Start from scratch” and prompt the agent Cursor creates an Origin repo in the background, gives you a live browser preview while it builds, and when you’re happy with it, you can: • Save the full project as a repo • Keep it private or internal • Continue building from the Codebase • Connect Vercel and deploy directly to a live URL Basically: Idea → prompt → working app → repo → deployed website

How are people using cloud agents with all the local skills and CLIs they have? I'm getting tempted to fully sync my MBP to Mac Mini, build my own connector and apps to use Codex, Claude, Cursor models from desktop and phone... Somebody talk me out of it.

Tip: Browsers & ports for cloud agents The "plug" icon appears for cloud Cursor sessions. It shows all the running processes and port mappings for that session, along with the local ports they're forwarded to (cursor does this ✨automatically✨) Select the globe icon to open that process into the Cursor browser - you can open the URL in any browser on your machine too! And that's the cool part - by default, all remote ports are available locally