2026 年 Agents Week
歡迎參加我們的 2026 年 Agents Week，一同慶祝 AI 智慧體的強大力量，並探索它們如何改變我們建構、保護及擴展網際網路的方式。
最新更新與公告
推出智慧體準備度分數 — 查看您的網站智慧體是否做好準備
智慧體準備度分數有助於網站擁有者瞭解其網站支援 AI 智慧體的情況。我們將在此探討新標準，分享 Radar 資料，並詳細介紹我們如何將 Cloudflare 文件打造成 Web 上最便於智慧體使用的文件。
Shared Dictionaries: Compression that keeps up with the agentic web
Running large LLMs across Cloudflare’s network requires us to be smarter and more efficient about GPU memory bandwidth. That’s why we developed Unweight, a lossless inference-time compression system that achieves up to a 22% model footprint reduction, so that we can deliver faster and cheaper inference than ever before.
Redirects for AI training: edge-enforcement of canonical content
Soft directives don’t stop crawlers from ingesting deprecated content. Redirects for AI Training allows anybody on Cloudflare to redirect verified crawlers to canonical pages with one toggle and no origin changes.
Introducing Flagship: feature flags built for the age of AI
We are launching Flagship, a native feature flag service built on Cloudflare’s global network to eliminate the latency of third-party providers. By using KV and Durable Objects, Flagship allows for sub-millisecond flag evaluation.
Agents that remember: introducing Agent Memory
Cloudflare Agent Memory is a managed service that gives AI agents persistent memory, allowing them to recall what matters, forget what doesn't, and get smarter over time.
Unweight: How we compressed a frontier LLM 22% without sacrificing quality
Running LLMs across Cloudflare’s network requires us to be smarter and more efficient about GPU memory bandwidth. That’s why we developed Unweight, a lossless inference-time compression system that achieves up to a 22% model footprint reduction, so that we can deliver faster and cheaper inference than ever before.
