Cloudflare Expands Agent Cloud to Power Scalable, Production-Ready AI Agents

Cloudflare has unveiled a major expansion of its Agent Cloud platform, introducing new tools and infrastructure aimed at helping developers build, deploy, and scale AI agents for enterprise use.

The move comes as the industry shifts from chatbot-based applications to more advanced autonomous agents capable of reasoning, coding, and executing multi-step tasks. However, existing infrastructure—often reliant on costly virtual servers or isolated containers—has struggled to support large-scale adoption.

Cloudflare said its enhanced Agent Cloud addresses these limitations by offering a unified stack spanning compute, storage, deployment, and security, enabling developers to move beyond experimental prototypes.

"The way people build software is fundamentally changing. We are entering a world where agents are the ones writing and executing code. But agents need a home that is secure by default, scales to millions instantly, and persists across long-running tasks. We’ve spent nine years building the foundation for this with Cloudflare Workers. Today, we are making Cloudflare the definitive platform for the agentic web," said Matthew Prince, Cloudflare co-founder and CEO.

Among the key updates is Dynamic Workers, a new compute model designed to run AI-generated code in lightweight, secure environments that spin up in milliseconds—offering faster and more cost-efficient execution than traditional containers.

The company also introduced Artifacts, a Git-compatible storage system built for AI-generated code, allowing developers to manage millions of repositories and provide persistent storage for agent workflows.

Cloudflare is further rolling out Sandboxes for full operating system environments and Think, a framework designed to support long-running, multi-step agent tasks.

“Cloud agents are quickly becoming a foundational building block for how work gets done, and with Cloudflare, we’re making it dramatically easier for developers to deploy, production-ready agents powered by GPT-5.4 and Codex to run real enterprise workloads at scale,” said Rohan Varma, OpenAI Product, Codex.

The expanded platform also enables developers to switch between AI models seamlessly, reflecting the rapidly evolving AI landscape.