Have questions, or building something cool with Cloudflare's Developer products? We're here to help. For help with your account please try @CloudflareHelp
A better internet depends on a diverse ecosystem. Today, we're proud to announce our support for @ladybirdbrowser (a completely independent browser built from scratch) and @OmarchyLinux (making Linux more approachable for devs). Super excited to see what the community builds!
Today, we’re excited to open-source an AI vibe coding platform, VibeSDK, to enable anyone to run an entire vibe coding platform themselves, end-to-end, with just one click
📣 This is not a drill: Email Sending is coming to Workers: just call email.send() - !
As part of this, we're combining Email Sending and Email Routing together into a cohesive, unified hub to manage emails.
Want to quickly prototype or build an app or agent with Workers + your favorite AI model?
We just published an example prompt you can use to get better results out of Claude, o1, o3-mini, Gemini, and Llama 3.3: developers.cloudflare.com/agents/build/p…
We're excited to introduce Cloudflare Sandboxes — the easiest way to run LLM generated code on demand.
Sandboxes make it easy to spin up new instances of containers (and soon Workers — stay tuned!!) to make it easy to spin up tens, hundreds, or thousands of code-running agents
We now have the DeepSeek-R1-Distill-Qwen-32B model on Cloudflare Workers AI! Use it to solve math, coding and complex reasoning tasks. It's open source, hosted on Cloudflare servers, and is comparable to OpenAI's o1-mini.
What makes it shine:
🌟 It solves math, coding and
New! The Browser Rendering REST API is live.
If you're building AI Agents, you can use it for:
✅ Capturing screenshots
📄 Generating PDFs
🔍 Extracting content
🤖 Scraping web elements
Learn more 👇
This is HUGE. Build bigger, more CPU intensive apps on Workers: our CPU limit is now 5 minutes per invocation (up from 30s).
This does not include time spent waiting on DB calls, external APIs, or LLMs: that doesn't count towards your CPU limits.
AutoRAG is now in open beta—fully-managed RAG pipelines so you can focus on building, not managing vector databases.
🗄️ Upload docs—we handle your embeddings and vector DB
🤖 Build AI chatbots with context-aware answers using API
👀 Monitor and analyze queries via AI Gateway