Cloudflare has announced support for Cursor Cloud Agents on Cloudflare Sandboxes, enabling developers and enterprises to run AI coding agents in secure, customer-controlled environments while maintaining existing development workflows.
The new integration strengthens Cloudflare’s positioning in the rapidly growing agentic AI infrastructure market, building on its support for platforms such as Devin Outposts and Claude Managed Agents. The move gives organizations greater control over where AI agents execute tasks and how they access source code, systems, and sensitive credentials.
With the integration, developers can continue using Cursor’s familiar interface across desktop, web, and mobile applications to assign coding tasks. While Cursor manages AI inference, orchestration, and planning, the execution of agent tasks takes place within Cloudflare Sandboxes, isolated environments hosted inside a customer’s Cloudflare account.
“Developers want powerful AI tools that fit naturally into their workflows, and enterprises need those tools to run in environments they control.”
– Dane Knecht, Chief Technology Officer, Cloudflare
According to Cloudflare, the offering addresses a growing enterprise requirement for secure AI deployment. As organizations increasingly adopt AI-powered coding assistants, concerns around data governance, code security, build caches, and secret management have become critical considerations.
“Bringing Cursor Cloud Agents to Cloudflare Sandboxes is another step toward making Cloudflare the execution layer for the next generation of agentic applications,” said Dane Knecht, Chief Technology Officer at Cloudflare.
SpaceXAI, the company behind Cursor’s Self-Hosted Machines capability, highlighted the importance of giving development teams flexibility without compromising control. The platform allows organizations to route AI workloads to infrastructure they operate while preserving the Cursor experience.
The integration also supports enterprise-scale deployments through worker pools, orchestration capabilities, and APIs, allowing organizations to manage AI agent workloads across multiple environments.
