All news with #cloudflare tag

🛠️ Cloudflare announced developer experience improvements to AI Search, automating the assembly of Workers AI, AI Gateway, Vectorize, R2, and Browser Run so teams can deploy search instances out of the box. The update includes public /search and /mcp endpoints, optional Cloudflare Access for private instances, and multi-instance querying via Workers or public endpoints. A pricing preview is provided, with embedding and reranking free on default models while in beta.

🔎 Cloudflare outlines the rise of software agents as a new class of web visitors and presents the concept of an "Agentic Internet" built to be readable, discoverable, callable, and payable. The post describes open standards and tools—like Web Bot Auth, PACT, Markdown for Agents, WebMCP, and Monetization Gateway—that enable cooperation between agents and domain owners. Cloudflare positions itself as a neutral platform offering these primitives while advocating for an open, standards-based future.

🛰️ Kitesurf is a new browser built by Cloudflare to run entirely on top of Workers and optimized for AI agents. It targets agentic tasks by being far more efficient in CPU and memory than Chromium for common operations like screenshots and HTML extraction. The design emphasizes isolation, stateless components, robust exception handling, and extensive testing using Web Platform Tests plus integration and visual regression suites. Kitesurf’s architecture separates the Engine, PageScript, and PageRenderer, uses Rust-compiled WebAssembly where possible, and enforces network access through a SandboxOutbound worker to minimize risk.

🤖 Cloudflare explains that customers increasingly find businesses via AI assistants rather than human-led search, so site owners must optimize for agent discoverability. The company has integrated Agent Readiness diagnostics and a new Answer Engine Optimization (AEO) tool into the Cloudflare dashboard to show how agents read, fetch, and recommend sites. These tools run checks against robots, sitemaps, headers, and machine-readable content, simulate assistant queries (e.g., Anthropic, OpenAI), and provide actionable remediation steps with links to Cloudflare settings or copyable prompts. The AEO feature benchmarks your category against competitors, measures citations and referral behavior, and surfaces operator crawl and referral patterns so you can iterate and improve recommendations.

🔧 Cloudflare is launching a developer preview of WebMCP, a browser standard that exposes a document.modelContext surface to enable AI agents to interact with sites without changing origin code. With a single toggle in the Cloudflare Dashboard, an edge injection adds a small bridge script that registers tool packs in the visitor's browser. Two packs—Content Credentials and Site MCP Server—run entirely client-side in this preview, while future packs may call edge workers for heavier tasks.

🔒 Cloudflare reports it was named the only vendor recognized as a Visionary in both the 2026 Gartner Magic Quadrant for SASE Platforms and the 2026 Gartner Magic Quadrant for Security Service Edge. The post credits customer feedback and highlights Cloudflare One’s unified SASE architecture, built-in AI agent governance, native post-quantum encryption, and predictable pricing. It argues that modern SASE must be composable, programmable, and ready for agentic operations and quantum threats.

🧭 Sam Rhea, Cloudflare’s CIO, describes how the company built Cloudflare OS to enable safe, productive AI use across teams. Initially cautious in 2025, the company accelerated when powerful AI agents emerged, prompting internal pilots for engineers and non-engineers. Cloudflare OS combines off-the-shelf components with custom services, a contextual Codex for engineering, and a Model Context Protocol to enforce scoped permissions. The platform routes model calls through an AI Gateway for filtering, logging, and cost and model controls.

🛡️ Cloudflare announces Identity-aware AI Gateway with Cloudflare Access in open beta and User Insights generally available to AI Gateway customers. The integration attaches verified user identities to each request as cf.user_id, enabling per-user spend limits, filtering, and auditing. AI Gateway centralizes model access (OpenAI, Anthropic, Google, Workers AI) and routes agent harnesses like Copilot through a single control plane. User Insights builds behavioral baselines from traffic to surface anomalous accounts and cost inefficiencies without blocking traffic.

🛡️ Cloudflare describes WriteGuard, a centralized policy, attribution, and auditing layer for MCP servers now available in private beta. It sits between MCP clients and tool handlers to classify calls by risk, attach agent attribution, scrub audit events, and block dangerous actions before execution. The post explains how WriteGuard integrates with existing identity flows, per-tool configuration, and an asynchronous audit Worker to make agentic writes visible and controllable across MCP-connected systems.

🛠️ Cloudflare OS provides each employee with an agent-backed workspace grounded in company context, skills, and systems. It supports agent-driven docs, apps, and workflows while enforcing security via Gatekeepers and observation-based access control. The platform runs server code in Dynamic Workers and client code in sandboxed frames, integrates with MCP and AI Gateway, and is open sourced for organizations to deploy and customize.

🛰️ Cloudflare announces a unified Agents experience to deploy, observe, and manage hosted agents, starting with agent-level observability. The platform adds agent-aware tracing that captures model calls, tool executions, token usage, and subagent behavior alongside existing Workers infrastructure spans. Integrations for Think, Flue, and AI SDK emit traces to the dashboard or OTLP destinations, and recording controls let you exclude sensitive payloads. Tracing is free in beta and will be folded into Workers Observability pricing from October 1, 2026.

🔍 Cloudflare now captures OpenTelemetry traces automatically during local Worker development in Wrangler and Vite. When a supported coding agent session is detected, the development server exposes a Local Explorer API that lets agents query traces and correlated logs without installing SDKs or configuring observability. The Local Explorer also offers a browser interface to inspect spans, timing, attributes, errors, and local state for D1, KV, R2, Durable Objects, and Workflows.

🛠️ Cloudflare introduces the CI SDK built on Workflows to run CI pipelines directly on its platform. The system ties Artifacts (versioned code storage) to Workflows so repository pushes can trigger CI jobs, with sandboxed steps, dependency caching, and parallel execution. Platforms can manage CI for many repos while allowing customers to run custom Workflows in the same namespace. The CI SDK supports self-healing agents, R2-backed caches, and improved observability in the Workflows dashboard.

🚀 Cloudflare describes how AI agents are transforming the Software Development Lifecycle and introduces the Agent Development Lifecycle (ADLC). The post argues agents can and should manage more of the SDLC, and presents Cloudflare Workflows and Artifacts as primitives to orchestrate complex, long-running processes. It frames software factories as the future of autonomous software delivery and invites developers to experiment with @cloudflare/ci and agent-driven workflows.

🛠️ Cloudflare ran an automated triage pipeline on the Astro repository, using isolated AI subagents to read, reproduce, diagnose, and ship preview fixes for incoming bug reports. The pipeline—implemented as a GitHub Action and generalized into the Flue framework—reduced open issues from over 200 to about 30 and aims for zero. The system emphasizes transparency, sequential reasoning, and maintainability, and the triage logic was extracted into a standalone repo, triagebot-action, for reuse and adaptation.

🔎 Over four months, Cloudflare’s AI code reviewer flagged nearly 230,000 deviations from internal engineering standards and blocked almost 16,000 merges. The company consolidated dispersed guidance into the Cloudflare Codex, a governed RFC-based repository of SHOULD and MUST requirements that agents can consume across the engineering lifecycle. Codex-driven agents now review code, specs, and incident reports, improving consistency and surfacing issues earlier while leaving final judgment to engineers.

🔐 Cloudflare introduces Wallets to give AI agents stable identities and payment capabilities for buying APIs and content. Account Wallets hold funds and set policies while Virtual Wallets let agents spend within defined guardrails. Wallets integrate with the Monetization Gateway and x402 micropayments to enable low-friction, machine-native commerce and optional human-readable agent handles.

🔎 Analysis of 4 million dynamic reports shows nearly half (45.32%) of malware with C2 activity connects directly to IP addresses, bypassing DNS. This behavior—seen in ransomware droppers, P2P botnets and IoT threats—evades DNS-based defenses. The article introduces zero trust IP (ZT-IP), a network-level enforcement model that permits only DNS-sanctioned outbound IP connections and validates its efficacy against real-world samples and traffic.

🖥️ Today Cloudflare announced an early preview of @cloudflare/computer, a runtime that gives each agent a virtual "computer" — a primed filesystem and selectable execution environments. The package uses Durable Objects and isolates as the primary, horizontally scalable compute primitive while optionally attaching containers for heavier tasks. It provides a durable filesystem, tools (read, write, edit, ls, exec), and multiple execution backends, aiming to minimize container usage and improve efficiency for agentic systems.

🔧 Cloudflare describes techniques to serve demanding long-context models like Moonshot's Kimi and Z.ai's GLM efficiently by reducing memory use and protecting shared caches. They run experiments with SGLang and separate prefill and decode phases. Key optimizations are FP8 KV-cache quantization, INT4 weight compression for decode, and KV cache integrity checks to prevent cross-request corruption, all while preserving model accuracy.