Eng

On June 27, the United Nations celebrates Micro-, Small, and Medium-sized Enterprises Day (MSME) to recognize the critical role these businesses play in the global economy and economic development. According to the World Bank and the UN, small and medium-sized businesses make up about 90 percent of all businesses, between 50-70 percent of global employment, and 50 percent of global GDP. They not only drive local and national economies, but also sustain the livelihoods of women, youth, and other groups in vulnerable situations. ...

When query performance degrades, most engineers tend to reach for the application code first to identify issues.  However, the root cause can also reside closer to the data at the storage level, and indexing could be the difference between a targeted lookup and a blind table scan that negatively impacts performance. With the right index in place, a query that once sifted through millions of rows can return results in milliseconds. ...

Developing a new video conferencing application often begins with a peer-to-peer setup using WebRTC, facilitating direct data exchange between clients. While effective for small demonstrations, this method encounters scalability hurdles with increased participants. The data transmission load for each client escalates significantly in proportion to the number of users, as each client is required to send data to every other client except themselves (n-1). In the scaling of video conferencing applications, Selective Forwarding Units (SFUs) are essential. Essentially a media stream routing hub, an SFU receives media and data flows from participants and intelligently determines which streams to forward. By strategically distributing media based on network conditions and participant needs, this mechanism minimizes bandwidth usage and greatly enhances scalability. Nearly every video conferencing application today uses SFUs. ...

Since June 9, 2025, Internet users located in Russia and connecting to web services protected by Cloudflare have been throttled by Russian Internet Service Providers (ISPs). As the throttling is being applied by local ISPs, the action is outside of Cloudflare’s control and we are unable, at this time, to restore reliable, high performance access to Cloudflare products and protected websites for Russian users in a lawful manner. Internal data analysis suggests that the throttling allows Internet users to load only the first 16 KB of any web asset, rendering most web navigation impossible. ...

<div> <h2>What even <i>is</i> an Agents SDK?</h2> <a href="#what-even-is-an-agents-sdk"> </a> </div> <p>The AI landscape is evolving at an incredible pace, and with it, the tools and platforms available to developers are becoming more powerful and interconnected than ever. Here at Cloudflare, we're genuinely passionate about empowering you to build the next generation of applications, and that absolutely includes intelligent agents that can reason, act, and interact with the world.</p><p>When we talk about "<b>Agents SDKs</b>", it can sometimes feel a bit… fuzzy. Some SDKs (software development kits) <b>described as 'agent' SDKs</b> are really about providing frameworks for tool calling and interacting with models. They're fantastic for defining an agent's "brain" – its intelligence, its ability to reason, and how it uses external tools. Here’s the thing: all these agents need a place to actually run. Then there's what we offer at Cloudflare: <a href="https://developers.cloudflare.com/agents/"><u>an SDK purpose-built to provide a seamless execution layer for agents</u></a>. While orchestration frameworks define how agents think, our SDK focuses on where they run, abstracting away infrastructure to enable persistent, scalable execution across our global network.</p><p>Think of it as the ultimate shell, the place where any agent, defined by any agent SDK (like the powerful new OpenAI Agents SDK), can truly live, persist, and run at global scale.</p><p>We’ve chosen OpenAI’s Agents SDK for this example, but the infrastructure is not specific to it. The execution layer is designed to integrate with any agent runtime.</p><p>That’s what this post is about: what we built, what we learned, and the design patterns that emerged from fusing these two pieces together.</p> <div> <h2>Why use two SDKs?</h2> <a href="#why-use-two-sdks"> </a> </div> <p><a href="https://openai.github.io/openai-agents-js/"><u>OpenAI’s Agents SDK</u></a> gives you the <i>agent</i>: a reasoning loop, tool definitions, and memory abstraction. But it assumes you bring your own runtime and state.</p><p><a href="https://developers.cloudflare.com/agents/"><u>Cloudflare’s Agents SDK</u></a> gives you the <i>environment</i>: a persistent object on our network with identity, state, and built-in concurrency control. But it doesn’t tell you how your agent should behave.</p><p>By combining them, we get a clear split:</p><ul><li><p><b>OpenAI</b>: cognition, planning, tool orchestration</p></li><li><p><b>Cloudflare</b>: location, identity, memory, execution</p></li></ul><p>This separation of concerns let us stay focused on logic, not glue code.</p> <div> <h2>What you can build with persistent agents</h2> <a href="#what-you-can-build-with-persistent-agents"> </a> </div> <p>Cloudflare <a href="https://developers.cloudflare.com/durable-objects/"><u>Durable Objects</u></a> let agents go beyond simple, stateless functions. They can persist memory, coordinate across workflows, and respond in real time. Combined with the OpenAI Agents SDK, this enables systems that reason, remember, and adapt over time.</p><p>Here are three architectural patterns that show how agents can be composed, guided, and connected:</p><p><b>Multi-agent systems: </b>Divide responsibilities across specialized agents that collaborate on tasks.</p><p><b>Human-in-the-loop: </b>Let agents plan independently but wait for human input at key decision points.</p><p><b>Addressable agents: </b>Make agents reachable through real-world interfaces like phone calls or WebSockets.</p> <div> <h3>Multi-agent systems </h3> <a href="#multi-agent-systems"> </a> </div> <p>Multi-agent systems let you break down a task into specialized agents that handle distinct responsibilities. In the example below, a triage agent routes questions to either a history or math tutor based on the query. Each agent has its own memory, logic, and instructions. With Cloudflare <a href="https://developers.cloudflare.com/durable-objects/"><u>Durable Objects</u></a>, these agents persist across sessions and can coordinate responses, making it easy to build systems that feel modular but work together intelligently.</p> <pre><code>export class MyAgent extends Agent { async onRequest() { const historyTutorAgent = new Agent({ instructions: “You provide assistance with historical queries. Explain important events and context clearly.”, name: “History Tutor”, }); ...

We’re excited to announce that Cloudflare Containers are now available in beta for all users on paid plans. You can now run new kinds of applications alongside your Workers. From media and data processing at the edge, to backend services in any language, to CLI tools in batch workloads — Containers open up a world of possibilities. Containers are tightly integrated with Workers and the rest of the developer platform, which means that: ...