Cloudflare, a leading connectivity cloud company, on Monday announced a range of offerings and a new acquisition to accelerate the development of AI agents. The company recently developed various solutions to help AI developers, such as an AI agent and a platform to build remote MCP servers.
Co-founder and CEO Matthew Prince said, “Cloudflare is the best place to build and scale AI agents. Period. The most innovative companies out there see that agents are the next big frontier in AI, and they’re choosing Cloudflare because we’ve got everything they need to move fast and build at scale on our Workers platform.”
The company published a few blog posts announcing the new developments. One of them highlighted the solutions to help developers build agents.
First, it added the ability to bring your own (BYO) authentication provider to build a remote MCP server through integrations with Stytch, Auth0, and WorkOS. Developers can also leverage hibernation for McpAgent instances to maintain connections for long-running sessions without paying for idle time.
Earlier available only in the paid plans, Durable Objects, a component that enables developers to create real-time experiences in their applications, is now available in the free tier.
The company introduced AutoRAG (in open beta), a managed solution for developers to integrate RAG into an AI application with just a few clicks. Cloudflare Workflows, a serverless execution engine that helps build applications, is now out of beta and generally available to all users for production.
Cloudflare also launched a new landing page for developers looking to build AI agents. Developers can find everything they need to build agents fast, and have the ability to scale up with ease.
Additionally, the company acquired Outerbase, a developer database company. This will help Cloudflare users easily build and deploy full-stack, AI-enabled applications backed by databases.
The post Cloudflare Just Made Building AI Applications and Agents Super Easy appeared first on Analytics India Magazine.
