Loading post…
CursorAnnouncement
Cursor Projects
Summary
Cursor is launching Projects, a beta feature for taking on larger bodies of work such as features, migrations, and full applications. Each Project preserves context over months, runs on its own cloud computer through Cloud Agents, and coordinates parallel subagents rather than having the coordinator write code itself. Shared files synchronize across agents’ cloud and local machines, storing research, artifacts, codebase knowledge, and preferred working practices so later agents can use them. Projects can also subscribe to Slack channels, schedules, or pull requests and delegate work when signals arrive, while local agents handle testing that requires the user’s machine. Projects are accessible from Cursor’s left-hand navigation and are rolling out to all users in beta starting today.
Context
Projects are designed for larger bodies of work, including features, migrations, and full applications. A Project keeps context over months and accumulates research, artifacts, codebase knowledge, and preferred working practices in shared files.
Approach / What changed
A coordinator agent plans work, creates and manages parallel implementation agents, and returns completed work for checking. Projects run on cloud computers through Cloud Agents, synchronize context across cloud and local machines, start local agents for machine-dependent testing, and can react to Slack messages, schedules, or pull requests.
Takeaways
The coordinator agent does not write code; it plans work, delegates implementation to agents, and brings completed work back for review.
Project files synchronize across every cloud and local machine used by its agents, allowing later agents to reuse accumulated research, artifacts, and testing instructions.
Subscriptions let a Project act without a prompt when it detects activity in a Slack channel, reaches a schedule, or sees a pull request.
FAQ
How does a Project divide work among agents?
A coordinator agent plans the work and creates or manages as many agents in parallel as needed. Those agents implement the work, while the coordinator brings the finished results back for checking.
What happens when a task needs testing on a local machine?
The Project runs primarily on its own computer in the cloud, so closing a laptop does not stop it. When local testing is needed, the coordinator spins up an agent on the user’s machine.
How can Projects start work without a prompt?
A coordinator can watch a Slack channel, run on a schedule, or follow pull requests. For example, connecting it to a bug-report channel makes it delegate work when a bug arrives.
Source and freshness
- Source
- cursor.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.