


Building the @aiSDK.


Introducing eve 1.0 Build production agents.
eve is generally available with v1.0. • Build agents on your own harness • Ship multi-tenant, multiplayer agents • Govern & trace sessions with Agent Runs • Render agent UIs via Next.js, Nuxt & more Read the blog → vercel.com/blog/eve-is-now-g…

Use Muse Ember with with AI SDK
1/ announcing our smallest, most efficient little model is here: muse ember 🔥 built for work that agents repeat all day, it gets you more intelligence per dollar than Haiku, Luna, and all other flash models at any reasoning setting and does it at a third of the cost or less!

Use Claude Fable 5.2 with AI SDK
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges. They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.

Generative UI for conversational agents. Combining @aisdk with Chat SDK and 𝚓𝚜𝚘𝚗-𝚛𝚎𝚗𝚍𝚎𝚛, you can go straight from LLM to UI on platforms like Slack and Teams. I believe this will become the dominant Human-Agent Interaction (HAI) paradigm: vercel.com/changelog/json-re…

In just 24 hours 🤯 ✓ 𝟲,𝟴𝟭𝟳 vulnerabilities identified ✓ 𝟱𝟴𝟬 critical or high ✓ 𝟭,𝟰𝟭𝟭 already patched by Agent Vercel Security Reviews are 100% free until Nov 10
Today we are launching Vercel Security Review in public beta. Run vulnerability reviews on every push, and ship fixes in one click with Vercel Agent. Read the blog → vercel.com/blog/vercel-secur…

elegant 👀
New `ai-tool-set` feature: tool activation reasons Your agent only sees the active tools It doesn't know what's hidden behind some toggles Each activation can now carry a reason why a tool is inactive Pass it to your model as extra context, so it can better guide the user

What terminology do you find most intuitive/understandable for differentiating between something like these two layers (e.g. in AI SDK)? 1. Top-level API which most devs use (e.g. streamText) 2. Provider implementation spec which provider adapter builders use (e.g. ProviderV4)



Use Jev to ask questions about images in AI SDK. Pass an image, define a boolean question, and get back the probability that it's true.
composable images: Jev got eyes!!! eyes eyes baby. not only are we enabling multimodality for future Jev models, we’re enabling it for the current Jev that you all know and love. and images can go anywhere text could go before, in whatever combination you can think of. go wild. deets in the docs: docs.typesafe.ai/go/images

Use the new @MiniMax_AI M3.1 Flash model with the AI SDK and AI Gateway for free.
MiniMax M3.1 Flash from @MiniMax_AI is live on AI Gateway for free. It is better at agentic tasks, coding, and cybersecurity. 𝚖𝚒𝚗𝚒𝚖𝚊𝚡/𝚖𝚒𝚗𝚒𝚖𝚊𝚡-𝚖𝟹.𝟷-𝚏𝚕𝚊𝚜𝚑 Free through Oct 22 when served by MiniMax. vercel.com/changelog/minimax…

Use Gemini 4 Argon with AI SDK
Gemini 4 Argon is now globally available. Built to solve your hardest problems from start to finish, the model brings frontier capabilities across coding, enterprise workflows, and cyber defense.



AI SDK just hit 30 million weekly downloads 🤯 Absurd how quickly it has grown over the last year: • December: 5 million • March: 10 million • August: 20 million • September: 30 million And despite that rapid growth, our open issue count has been dropping, thanks in large part to the factory that @lgrammel built! It's really fun to be building a project like this with a great team (shoutout to the 🐐s: @gr2m @felixarntz @aayushkapoor_ @nishimiya), and I'm excited about what's next for AI SDK.