Cloudflare, Inc. has announced support for running Cursor Cloud Agents on Cloudflare Sandboxes. The move aims to transform running AI coding agents in secure, customer-controlled environments.
Dane Knecht, chief technology officer at Cloudflare, said: “Cloudflare Sandboxes give teams the freedom to use the AI tools they prefer while giving organisations a secure, isolated place to run agent work. Bringing Cursor Cloud Agents to Cloudflare Sandboxes is another step toward making Cloudflare the execution layer for the next generation of agentic applications.”
Cursor Cloud Agents on Cloudflare Sandboxes
Cloudflare’s integration with Cursor Cloud Agents allows developers to run AI coding workloads in controlled, customer-managed environments through Cloudflare Sandboxes. Building on Cloudflare’s work with other AI agent platforms, the integration aims to give organisations an execution layer that enables greater control over where agent tasks run and how code, systems, build caches, and secrets are accessed.
With Cursor Self-Hosted Machines, developers can continue using the familiar Cursor app, web, or mobile workflow, while Cursor handles inference, planning, orchestration, and routing. Actual coding is executed inside a sandbox environment within the customer’s Cloudflare account.
The system uses outbound connectivity where a Cursor worker runs the Cursor CLI and establishes a long-lived HTTPS connection to Cursor’s backend.
Repositories, build caches, and secrets remain on customer-controlled machines, although model-read file chunks and agent artefacts such as screenshots, videos, and logs may be uploaded for display in pull requests and dashboards. Overall, the integration combines Cursor’s agent workflow with Cloudflare’s controlled infrastructure for more secure, flexible enterprise AI development.
“Self-Hosted Machines let teams keep Cursor workflows across desktop, web, and mobile while routing work to infrastructure they operate. Cloudflare Sandboxes give those teams an enterprise-grade option for running agent workloads in a controlled environment,” said Toni Adams, sr director of Partnerships at SpaceXAI.
