Cloudflare Developers

Building on Cloudflare just got a new home  → workers.cloudflare.com

We rebuilt our agentic chat backend, cutting P90 TTFT from 8000ms to 300ms with @Cloudflare's durable objects Find out why we gave every agent it’s own tiny database: highlightai.com/blog/agentic-c…

I've launched: pythonbyexample.dev just in time for @pycon . It's a place to learn Python via the magic of Cloudflare's Dynamic Workers.

We just made it EVEN EASIER to buy and configure a domain for your Cloudflare Workers.

Added two new official Replicate skills: build-models + publish-models. They teach agents (and humans) how to package custom AI models with Cog and push them to Replicate, using the patterns and tools we use internally for production models. $ npx skills add replicate/skills github.com/replicate/skil…

love to see content like this building on top of the @cloudflare Agents SDK

Security engineers have tons of logs in buckets, 👀 here I am searching them directly in @cloudflare R2 and avoiding egress fees... (but it works in S3 and GCS too)

Multiple security vulnerabilities affecting React Server Components and Next.js have been disclosed. We strongly recommend updating your applications immediately. Cloudflare WAF managed rules already mitigate the disclosed denial-of-service vulnerabilities, and we are investigating additional coverage for several other CVEs. developers.cloudflare.com/changelog/post…

Come check out how @kristianfreeman is synthesizing information with @opencode using kimaki (built by @__morse) via @discord on the pilot episode of The Clanker Chronicles

built on @cloudflare sandboxes 🔥

workers ai is top 3 fastest providers for kimi k2.6, benchmarked by @ArtificialAnlys artificialanalysis.ai/models/kimi-k2…

My sitemogging website was on the front page of Hackernews for a while last Friday... Of course it was built on Cloudflare. How much do you think it cost me to run thousands of Workers AI + Browser Run sessions?!

"Agents can now create Cloudflare accounts, buy domains, and deploy" Here's how it works in 4 minutes.

Congratulations to the folks at @inworld_ai ! Realtime TTS-2 is on @Cloudflare on Day 0! Try now: developers.cloudflare.com/ai/models/inwo…

What else is in 2.0: - 90+ languages (up from 15) - Better alphanumerics for phone numbers, SKUs, codes - Improved word error rate & alignment - Inline non-verbals: [laugh] [sigh] [clear throat]

New in 2.0 is natural-language steering — use plain English to describe the tone, pace, and emotion. [speak as if barely holding back rage] I have told you. Repeatedly. [overwhelmed with excitement] We just hit a million users! Describe text granularly like: [very fast] [whisper] [falling pitch] or, combine them into one description: [say sadly with deliberate pauses in a low voice]

Realtime TTS 2.0 from @inworld_ai is now live on Cloudflare AI Gateway. Generate natural-sounding, steerable text-to-speech. Try it now: developers.cloudflare.com/ai/models/inwo…

Gemini API meets Cloudflare Workers: github.com/google-gemini/…

A couple of weeks ago I had the chance to host the Developer Track at Cloudflare Connect London. We had a presenters from Cloudflare and various customers. Now seems like a good time for a short thread with the slides from the various sessions.

Introducing Flue — The First Agent Harness Framework Flue is a TypeScript framework for building the next generation of agents, designed around a built-in agent harness. Flue is like Claude Code, but 100% headless and programmable. There's no baked in assumption like requiring a human operator to function. No TUI. No GUI. Just TypeScript. But using Flue feels like using Claude Code. The agents you build act autonomously to solve problems and complete tasks. They require very little code to run. Most of the "logic" lives in Markdown: skills and context and AGENTS.md. Flue is like Astro or Next.js for agents (not surprising, given my background 🙃). It's not another AI SDK. It's a proper runtime-agnostic framework. Write once, build, and deploy your agents anywhere (Node.js, Cloudflare, GitHub Actions, GitLab CI/CD, etc). We originally built Flue to power AI workflows inside of the Astro GitHub repo. But then @_bgiori got his hands on it, and we realized that every agent needs a framework like Flue, not just us. Check it out! It's early, but I'm curious to hear what people think. Are agents ready for their library -> framework moment?

hard to believe we only launched big models on workers ai ~1.5 months ago. the craziest part about making models more efficient is that it's better for our users (faster and cheaper), but also better for us as an inference provider. we effectively reduced our hardware costs through software optimizations. this sounds easy but is really hard in practice - there is so much to do in this space, and so much we're learning and patching as we go. as we build the foundation for serving big models, the new models that come out inherit our efficient architecture too. if you want to join the challenge - we're hiring if you want to consume these models and don't want to be an MLE/SRE, happy to chat