Daniel and 10 others

We revamped our (previously experimental) telemetry: - no OTel dependency in AI SDK (if you want OTel you can register our OTel integration, genai standard comaptible) - automatic emitting to the node diagnostics channel - telemetry integrations can be more custom and powerful

AI SDK 7 canary has a new telemetry system. Register telemetry once, then all AI SDK calls emit telemetry by default.

@visakanv I wonder if this knowledge can be used to aid in progression as well: does wearing the "next level up" clothes help you attain that level faster?

have yall noticed that there’s gym outfit tier list that corresponds with the “level” that the gymgoer is at? people seem to unlock new levels of outfits at new levels of fitness. I notice this at the pool too, like only good swimmers wear bold neon colors

Introducing create-desktop-app Create personal applications that integrate natively with your operating system and can be opened via raycast npx create-desktop-app

Vercel Sandbox firewall can now proxy and filter outbound requests. ▪︎ Control all agent traffic from your own proxy ▪︎ More granular credential injection ▪︎ Log and audit outgoing traffic vercel.com/changelog/verc…

Despite being told no, I'm open-sourcing TrustClaw. You can now deploy a production-ready personal agent service with over 1000+ app integrations in a single command, straight to @vercel with npx @composio/trustclaw deploy I was inspired by @openclaw to build a simple web app where anyone could create their own 24/7 personal assistant and connect it to Gmail, Google Calendar, Notion, Slack, GitHub, HubSpot, Linear… well everything, and securely through OAuth/sandbox execution. It went viral on X, reached over a thousand users in less than 48h, and revenue began pouring in. If you are thinking like a company, you'd probably keep that locked up. But why should I be the reason you spend another year scrolling instead of building? So today, I'm open-sourcing TrustClaw anyway. > 24/7 agents that act across Gmail, Notion, GitHub, Slack, Linear, Jira, and 1000+ apps > OAuth and sandboxed execution, so users don't have to hand agents passwords or raw API keys > Supports multiple users and authentication right outside of the box with @better_auth Repo is open, MIT licensed. If I were starting an AI company today, I'd clone this, pick a market, and begin shipping with Claude Code. Honestly so excited to see what comes out of this.

Giving agents access to secrets inside the sandbox

built a basic tui for ai sdk 7 agents

Command Code is now the 4th most used coding agent beating Kilo, OpenCode, Roo Code, and Hermes agent on Vercel AI Gateway!! three reasons i could think why: 1. First of all, yes we're going open source soon 2. Our $1 Go plan with open models is the best AI coding deal on the market. Period. 3. While other agents only cater to top commercial models, Command Code is probably the best harness purpose built for open models. More in my eng deep dives¹ on repair harness engineering below.

Introducing Zenbu.js - The framework for hackable software I wanted the ability to edit the software I use with my coding agents, from there Zenbu.js was born Zenbu.js allows you to build desktop apps that can be modified by users after installation. This is made possible by: - shipping the app's raw source code to the user - a built in plugin system for your apps npx create-zenbu-app@latest

Introducing 𝚟𝚎𝚛𝚌𝚎𝚕 𝚖𝚎𝚝𝚛𝚒𝚌𝚜: query Observability Plus metrics via the Vercel CLI. Give your agents access to: • Query your observability data • Analyze your app performance • Debug issues vercel.com/changelog/verc…

ai sdk 7 canary: typed tool context tools can define and use a typed context that is separate from the llm generated input (e.g. for api keys)

AI SDK now has a canary release channel. Try early AI SDK 7 APIs and give us feedback.

excited about the new features and improvements in ai sdk 7

I neeeeed the most chronically online person you know. I'm hiring a media engineer to lead our social strategy at @vercel you must be: • chronically online • comfortable being onscreen/on video • obsessed w/ posting & building in public tag ur faves 🫶 or apply below!

deepsec is very cool! I ran it against our main backend repo at @khanacademy and it found some really interesting edge cases. Spun up an agent team in Claude and addressed all the high-impact issues. This likely would've been a multi-week, or month, effort otherwise!

@gary__tyr @RhysSullivan Gotta lock down test modifications 🤣

@techwraith @RhysSullivan return 200; I've validated that p99.9 has improved significantly. Removed all external dependencies. Ensured no errors. I've modified 7 now incorrect test cases.

what are you guys using /goal for? i haven't tried it yet but i can't imagine letting the agent run for 12+ hours produces code that's anywhere near shippable

Sometimes the best way to build a UI for an agent is to not build the UI at all. I built an AI agent starter that lives in iMessage. Built on @nitrojsdev + Vercel @workflowsdk + evlog - Durable execution - Auto-retry on errors - Full observability git.new/nitro-agent

AI Gateway lets you route to any model. On May 13 in SF, we're hosting a builder night powered by those models. Pick one, build, demo. Audience votes on best build. With @AnthropicAI, @MiniMax_AI, & @Kimi_Moonshot Sign up ↓ luma.com/ttrgmjaf