Run cloud agents in your own infrastructure

Summary

Cursor has made self-hosted cloud agents generally available, allowing code, tool execution, and build artifacts to remain within an organization’s network. Each agent runs in an isolated virtual machine or dedicated worker with a terminal, browser, and full desktop; it can clone repositories, configure environments, write and test code, and push changes for review. A worker connects outbound to Cursor’s cloud over HTTPS, receives tool calls from the agent harness, and returns execution results, while organizations can run long-lived or single-use workers and manage large fleets through a Helm chart, Kubernetes operator, or fleet management API. The product retains cloud-agent capabilities including multi-model support, plugins, and team permissions, while giving teams access to internal caches, dependencies, endpoints, and security controls without maintaining a separate agent stack.

Takeaways

1. 1

   Workers connect outbound via HTTPS, so self-hosted agents require no inbound ports, firewall changes, or VPN tunnels.

2. 2

   Each agent session receives a dedicated worker that can be long-lived or single-use, supporting parallel workloads without machine sharing.

3. 3

   Organizations can scale workers with a Kubernetes WorkerDeployment or use the fleet management API to monitor utilization and build autoscaling on other infrastructure.