Cursor's Self-Hosted Machines Keep Agent Tool Execution Inside Your Own Network

In a September 2 changelog entry, Cursor described a setup that keeps cloud agents' tool execution entirely within your own network. It comes in two forms — My Machines for individuals and Team pools for organizations — and supports computer use on Linux and Mac.

Cursor AI-agent coding security enterprise

In a changelog entry dated September 2, 2026, Cursor described self-hosted machines, a setup that lets you keep tool execution entirely within your own network¹.

What stays on your side: your codebase, build outputs and secrets all stay on internal machines running in your infrastructure, while the agent handles tool calls locally¹
Two forms: My Machines connects a single laptop or VM to your account for personal workflows. Team pools are named queues of workers for a team or enterprise — capacity grows as requests arrive and shrinks when workers disconnect. Pools are not tied to one repository, and they can hibernate idle machines, then restore within a reconnect window when a follow-up arrives¹
Where it runs, and computer use: cloud agents can execute on infrastructure you already use, including AWS Lambda, Coder, Cloudflare, Daytona, Modal, Namespace, Vercel and E2B. Self-hosted workers support computer use on Linux and Mac — with the right desktop packages, an agent can click, type, take screenshots and drive the browser¹

Not being able to place code in an external execution environment has been one of the things that decides whether an organization can adopt a cloud coding agent at all. This entry offers those organizations a path to using agents while keeping execution in-house. The changelog gives no pricing or plan availability¹. Cursor also made it possible in August to start cloud agents without a GitHub connection, continuing a run of changes around where agents run.

Sources

Self-hosted machines - Cursor official changelog (September 2, 2026)