Agents that remember: introducing Agent Memory
As developers build increasingly sophisticated agents on Cloudflare, one of the biggest challenges they face is getting the right information into context at the right time. The quality of results produced by models is directly tied to the quality of context they operate with, but even as context window sizes grow past one million (1M) tokens, context rot remains an unsolved problem. A natural ten
Introducing Flagship: feature flags built for the age of AI
Introducing Flagship: feature flags built for the age of AI2026-04-17 AI is writing more code than ever. AI-assisted contributions now account for a rapidly growing share of new code across the platform. Agentic coding tools like OpenCode and Claude Code are shipping entire features in minutes. AI-generated code entering production is only going to accelerate. But the bigger shift isn't just speed
Artifacts: versioned storage that speaks Git
Agents have changed how we think about source control, file systems, and persisting state. Developers and agents are generating more code than ever — more code will be written over the next 5 years than in all of programming history — and it’s driven an order-of-magnitude change in the scale of the systems needed to meet this demand. Source control platforms are especially struggling here: they we
Cloudflare WorkersのCron Triggersでリリース当番通知botを構築した事例
なるべく登場する要素を少なくし、Cloudflare Workersの部分にロジックを集中させました。 素のfetchでSlack Webhook URLにリクエストを送るCloudflare Workersのサーバーレス関数を、定期的にCron Triggersから呼ぶだけ ツール導入前の課題 プロダクトのリリース担当が決まっておらず、「直近で機能開発を行ったメンバー」が自主的に行っていた その結果、タスクのアサイン状況によってリリース担当が暗黙的に決まる状態となり、不均衡が発生していた リリース担当が固定化されることによる課題 業務時間内で、リリース作業にかかる時間の割合の均等性が失われていた リリース作業に対する理解度の均等性が失われていた よくリリース作業を行っているメンバーの不在時に、緊急時のHotfix対応が必要になった場合に作業がうまく行えないリスクがあった どのような状態を
Replicate is joining Cloudflare – Replicate blog
Big news: We’re joining Cloudflare. Replicate’s going to carry on as a distinct brand, and all that’ll happen is that it’s going to get way better. It’ll be faster, we’ll have more resources, and it’ll integrate with the rest of Cloudflare’s Developer Platform. The API isn’t changing. The models you’re using today will keep working. If you’ve built something on Replicate, it’ll keep running just l
Partnering to make full-stack fast: deploy PlanetScale databases directly from Workers
We’re not burying the lede on this one: you can now connect Cloudflare Workers to your PlanetScale databases directly and ship full-stack applications backed by Postgres or MySQL. We’ve teamed up with PlanetScale because we wanted to partner with a database provider that we could confidently recommend to our users: one that shares our obsession with performance, reliability and developer experienc
Cloudflare Workers Tech Talks in Hokkaido #1 - Yusuke Wada
I hosted "Workers Tech Talks in Hokkaido #1" on September 4. It was the first Workers Tech Talks held in Hokkaido, Japan's northernmost region known for its beautiful nature and delicious food, particularly seafood and dairy products. About 32 people joined, creating a wonderful atmosphere. We had 5 main talks covering various aspects of Cloudflare Workers development. Everyone was engaged and lis
Containers are available in public beta for simple, global, and programmable compute
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
Mastra アプリを Cloudflare Workers にデプロイする | t28.dev
Fairy (AI エージェント) を作るメモまとめ > Mastra アプリを Cloudflare Workers にデプロイする npx create-mastra@latest で local で動く Mastra アプリは秒で作れた ので、これを Cloudflare Workers にデプロイしてインターネットからアクセス出来るようにする。 // こんな感じの mastra を Cloudflare Workers にデプロイしたいってわけ export const mastra = new Mastra({ workflows: { weatherWorkflow }, agents: { fairy, weatherAgent }, storage: new LibSQLStore({ // stores telemetry, evals, ... into memory
MastraでAgentをCloudflareにデプロイしてみる | DevelopersIO
Introduction Mastraは、TypeScriptでAIエージェントを開発できるフレームワークです。。 モデルのルーティング機能を持っていたりRAG対応していたり各種サーバレスサービスに対応していたり、 いろいろと機能があり、最近話題になってます。 本稿では、Mastraを使って簡単なAgentを作成し、Cloudflare Workersにデプロイしてみます。 Mastraの詳細な機能については、以下の記事を参照してください。 Mastraの基本機能と何ができるか Mastraで作るAIエージェント入門 Environment MacBook Pro (14-inch, M3, 2023) OS : MacOS 14.5 bun : 1.2.5 Node.js v20.0以降がPrerequisitesとありますが、 Bunで動いたのでそれを使います。 また、Cloudfla
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
https://x.com/i/status/2052334257725739226
Declare required secrets in your Wrangler configuration
Workers are no longer limited to 1000 subrequests
New Placement Hints for Workers
https://market-live.pages.dev/
Markdown Conversion
404 - Page Not Found
Rate Limiting in Workers is now GA
Workers for Platforms
Run AI-generated code on-demand with Code Sandboxes (new)