We knew we could not depend on every employee to configure every agent perfectly or watch every tool call. Before expanding write access across our own internal MCP servers, we built WriteGuard. We are now bringing those controls to Cloudflare MCP server portals. https://cfl.re/3TE4NvA

WriteGuard: fine-grained controls for MCP Servers

If your organization is adding write tools to MCP servers and wants to test these controls with us, sign up for the WriteGuard private beta.

blog.cloudflare.com

Yes, the day is not over yet: Identity-aware AI Gateway is now in open beta. User Insights turns that traffic into a behavioral baseline for every person and agent, and flags insider risk the moment it appears. https://cfl.re/4xrtUAt

Catching rogue AI behavior with identity-aware analytics

This is a security problem as much as a financial one. Solving these issues takes two things: a verified identity on every request (so a spike has a name behind it), and a picture of what normal looks like for that identity. Today we're announcing both.

blog.cloudflare.com

Cloudflare OS is an open-source platform that lets everyone in your company build apps, automate work, and safely access internal systems, shaped around what your organization knows and how it operates. https://cfl.re/4fGBl0w

Cloudflare OS: an open platform for agents, apps, and work

Cloudflare OS gives every person an agent and workspace built around their company: how it works, what it knows, and the systems it relies on.

blog.cloudflare.com

We built Cloudflare OS to equip our teams to safely rethink how they get work done with AI. The platform brings together the best of our technologies, from our Compute primitives to our Zero Trust suite. https://cfl.re/4wRzk7G

How we’re rethinking work at Cloudflare with Cloudflare OS

We are excited to share Cloudflare OS with you today, and we expect it to continue to evolve, quickly, as we learn more together.

blog.cloudflare.com

The Agent Access Model proposes a new architecture to secure task-scoped agents using strict identity brokering, continuous mediation, and stateful trust. https://cfl.re/4fXxafN

The Agent Access Model

The agent is instrumented software. The people represented in its context retain their privacy rights, and their data remains subject to governance requirements.

blog.cloudflare.com

Read how Jooble partnered with Cloudflare and Cloudfresh to process 125 million daily requests across 66 countries and block 7 million malicious bots every day. https://cfl.re/4xpFa0d

Jooble & Cloudflare | Customer Story

Discover how Jooble partnered with Cloudflare to optimize performance for 125 million daily requests and cut server load by 50%.

cloudflare.com

Cloudflare's Agents Cloud Week is here. To celebrate, we're offering $100 off Cloudflare Connect San Francisco (October 19-21). Use code CFAGENTS26 at registration - valid through August 9. https://cfl.re/4q4cV4M

By replacing manual issue verification with isolated AI subagents running in GitHub Actions, the Astro maintainers reduced open issue count by 85%. This post explores the architecture behind automated bug reproduction, patch verification, and preview releases. https://cfl.re/4wFuCKs

How we built a software factory to drive Astro’s GitHub issue count to zero

By replacing manual issue verification with isolated AI subagents running in GitHub Actions, the Astro maintainers reduced open issue count by 85%. This post explores the architecture behind automated...

blog.cloudflare.com

We created the Cloudflare Codex, a governed body of engineering standards that AI agents consume across the development lifecycle. By pairing structured RFCs with agentic reviews, teams automatically enforce consistency across code, specs, and incident reports. https://cfl.re/4yT9x0B

How Cloudflare enforces engineering standards using AI

We created the Cloudflare Codex, a governed body of engineering standards that AI agents consume across the development lifecycle. By pairing structured RFCs with agentic reviews, teams automatically ...

blog.cloudflare.com

Learn how to build customizable, sandboxed CI/CD pipelines natively on Cloudflare using Workflows, Artifacts, and the CI SDK. We walk through replacing complex YAML configurations with TypeScript workflow steps and self-healing AI agents. https://cfl.re/4heNriD

Run CI/CD for millions of repos — on your platform, on Cloudflare

Run CI/CD for millions of repos — on your platform, on Cloudflare

blog.cloudflare.com

Introducing Cloudflare Wallets. They will allow you to store stablecoins, purchase services, and receive funds across the web. https://cfl.re/45Kt8m1

Announcing Cloudflare Wallets: The programmable wallet for the agentic Internet

Cloudflare Wallets will provide AI agents with native payments and verifiable identity on the web. Using the x402 protocol, agents can autonomously purchase APIs and content within clear safety guardr...

blog.cloudflare.com

wrangler dev now produces structured traces for every local request. Your coding agent can hit a single API to pinpoint exactly what failed and why — no deployment required. https://cfl.re/4pTh63j

Your agent can now debug Workers with local tracing

wrangler dev now produces structured traces for every local request. Your coding agent can hit a single API to pinpoint exactly what failed and why — no deployment required.

blog.cloudflare.com

Cloudflare Agents brings all of your deployed agent sessions into a single experience, surfacing key information and insights into how your agents perform at scale. https://cfl.re/45Dp4UF

Introducing: Cloudflare Agents

Cloudflare Agents brings all of your deployed agent sessions into a single experience, surfacing key information and insights into how your agents perform at scale.

blog.cloudflare.com

Agents can write code faster than teams can review, deploy, and maintain it. Today we’re introducing the Agent Development Lifecycle and the Cloudflare primitives that underpin it. https://cfl.re/4hMuEv9

The Agent Development Lifecycle has arrived on Cloudflare

Get started with @cloudflare/ci, build an agent, and see how much of the SDLC you can make autonomous.

blog.cloudflare.com

Serving frontier models like Kimi and GLM means fighting for GPU memory. Here's how we quantize KV caches, compress model weights, and add integrity checks to serve them faster, cheaper, and safely. https://cfl.re/4bWZltY

Smaller, faster, safer: running Kimi and GLM at scale

Serving frontier models like Kimi and GLM means fighting for GPU memory. Here's how we quantize KV caches, compress model weights, and add integrity checks to serve them faster, cheaper, and safely.

blog.cloudflare.com

Analyze AI prompt content and intent to block sensitive corporate data from leaking into public models. https://cfl.re/45tzEgU

gRPC support is now available in Cloudflare Workers. You can now route, transform, and serve gRPC services natively at the edge without maintaining dedicated proxy infrastructure or translation layers. Read the launch post: https://cfl.re/4fMsitT

Cloudflare Workers and Containers now support inbound TCP connections and gRPC

Cloudflare Workers now support inbound TCP connections via Spectrum, allowing direct socket forwarding to Durable Objects and Containers. Developers can run full-duplex gRPC applications or leverage a...

blog.cloudflare.com

Programmatic billing visibility is now available. The new Billable Usage API gives Cloudflare Enterprise customers direct access to near real-time usage metrics across Workers, R2, and core products. https://cfl.re/4w4EP1W

Introducing the Billable Usage API: programmatic cost visibility for Cloudflare

Cloudflare has launched a new Billable Usage API for accounts, giving developers and FinOps teams single-endpoint programmatic visibility into cost and usage across all self-serve products. Built arou...

blog.cloudflare.com

Running large language models at the edge introduces latency and high compute costs. We are adding smaller, fine-tuned models to Workers AI—giving developers faster inference speeds and lower latency for specific tasks. Read the technical breakdown: https://cfl.re/4bWZltY

Smaller, faster, safer: running Kimi and GLM at scale

Serving frontier models like Kimi and GLM means fighting for GPU memory. Here's how we quantize KV caches, compress model weights, and add integrity checks to serve them faster, cheaper, and safely.

blog.cloudflare.com

You can now call methods defined in a Python Worker from a JavaScript Worker and vice versa. You can share objects across Python and JavaScript, and call methods on a Python object from TypeScript. It all just works. https://cfl.re/4hccinm

One coding agent can write a Python Worker and another can write a JavaScript Worker. At runtime, those Workers can exchange references to live objects and call their methods without defining APIs, schemas, or serialization code.

blog.cloudflare.com

Agents need more than just a container to scale. We're introducing @cloudflare/computer, an agent runtime that dynamically orchestrates between fast, efficient isolates and full Linux containers to give every agent a computer of its own. https://cfl.re/4w8ZcuX

Your agent needs a computer, not a container — introducing @cloudflare/computer

The @cloudflare/computer package provides an agent runtime where the details and mechanics of what code runs in an isolate, and what runs in a container sandbox are handled by the platform.

blog.cloudflare.com

Accelerate AI. 🤖 Not the chaos that comes with it. Safely adopt AI with the agile SASE platform. https://cfl.re/45tzEgU

Welcome to Agents Week, when we explore how cloud infrastructure must evolve to serve autonomous agents rather than human browsers. Join us as we unpack the storage, execution, and security primitives needed for an agent-native web. https://cfl.re/4wBLNfW #AgentsWeek

Welcome to Agents Week!

Follow along on the blog this week for the latest innovations around Agents, and reach out on X to join in the conversation.

blog.cloudflare.com

We’re honored to be named a Visionary in the Gartner® Magic Quadrant™ for SASE Platforms report for the second consecutive year! To us, this placement validates our commitment to an organically built, composable architecture. https://cfl.re/4eVIEQc

Last year, we brought Media over QUIC (MoQ) to our global network. Today, we’re adding isolated relays & pub/sub access controls, so you can run real applications. Deploy in seconds across 330+ cities—no servers or load balancers needed. Free in beta: https://cfl.re/4fPqMqZ

An API for MoQ: provision your own isolated relays

Last year we made every Cloudflare server a Media over QUIC (MoQ) relay. Now the new provisioning API lets you create your own isolated relay and control who can publish and who can only watch.

blog.cloudflare.com

Today is System Administrator Appreciation Day. Tag a sysadmin who has saved your bacon and say thank you. #CloudflareChat

We’re honored to be a Visionary in the 2026 Gartner® Magic Quadrant™ for Secure Access Service Edge Platforms! Check back soon for your complimentary copy.

Happy #InternAppreciationDay! 🧡 To all of our Cloudflare interns around the world: thank you for your curiosity, your fresh perspectives, and your impact. We’re so proud to be part of your career journey! 🚀 Check out our open early-talent roles at cloudflare.com/careers

We moved cdnjs, serving 9 billion requests a day, entirely onto Cloudflare's Developer Platform. That means we’re running one of the Internet's busiest open-source CDNs on our own building blocks, and we pushed Workflows and Workers limits higher for everyone. https://cfl.re/4yMW1LN

Dogfooding at scale: migrating cdnjs to Cloudflare’s Developer Platform

As of June 23, 2026, cdnjs, one of the Internet's busiest open-source CDNs, is running exclusively on Cloudflare’s Developer Platform.

cfl.re

Your team is already using ChatGPT & AI agents—are you actually securing it? Skip the theory. Join Chris O'Rourke (Cloudflare) & Justin Tibbs (Presidio) at #BHUSA for real-world Zero Trust AI controls. No product pitches—just practical strategy. 🗓️ Aug 5 | 4:45 PM 🔗 https://cfl.re/3TmmRKF