Guillermo Rauch

🆓 Sandbox data for downloads. Happy Friday! Time to ship more agents

Ship like @shadcn

Kimi K3 is the best performing model on http://nextjs.org/evals, ahead of Fable, reaching a comparable success rate in less time. This is the first time that an open model is ahead of all proprietary ones for this comprehensive web engineering benchmark. Notes: ▪️ Benchmarks don’t always tell the full story, although this is important signal, adding to mounting evidence that this could be a breakthrough moment for open models ▪️ No model as of yet has reached 100% completion on this set of evals. The top performer peaks at 92% and 96% “with help”

this is who runs this account 🧉

I’m excited to welcome two legends of developer tools, Pete Hunt (@floydophone) and Nick Schrock (@schrockn), to Vercel. Pete was one of the pioneers of @reactjs at Meta. He made an early bet to power Instagram Web with ⚛️ React, evangelizing it internally and externally. He will be running Frameworks and leading @nextjs. I couldn’t imagine a better person to lead React’s most popular framework to even greater heights. Nick co-invented @graphql, solving some of the gnarliest data infrastructure and access issues at Facebook scale, with a delightful developer experience. He will be working on Agentic Developer Experience, solving the problem of enabling the next billion agents and leading the way to a future of self-improving software. It’s a dream-come-true for a founder of a startup to welcome engineering minds of this caliber who are also wonderful humans. You probably want to work with them, and they’re hiring 😁. Their DMs are open, from job applications to bug reports!

The case for your own public agent, on your .com. 0️⃣ First, the anti-case. If you haven't shipped high quality APIs for agents, start there. OpenAPI specs, SDKs, CLIs and MCPs as appropriate. 1️⃣ Convenience. Not every customer has a harness 'at the ready' for every possible interaction with your product and company. Shipping one on your own domain covers a lot of spontaneous requirements. 2️⃣ Security. When you go to 𝚟𝚎𝚛𝚌𝚎𝚕.𝚌𝚘𝚖 and talk to Agent, we put in the work to cover audit trails, a least-privilege permission model, and extra assurances to ensure security, privacy and data integrity. It's fully cloud-based and sandboxed, vs. a sprawl of static credentials on users' machines. 3️⃣ Proactivity. We're still in the "human enters prompt" phase of AI. Our cloud-based agent can act on anomaly alerts triggered by exceptions, attacks, usage spikes. Our agent needs to monitor your infra while you sleep. You can, of course, set up workflows and schedules with your own harnesses, but it gets much harder. I think it's ultimately a sequencing thing. I agree with Mitchell that the priority is to give users choice and flexibility. We give people http://vercel.com/plugin to integrate with every agent out there. Our CLI and MCP are constantly improving. Our own Agent re-uses the same http://skills.sh everyone gets. All our sites are Markdown-over-the-wire if you're an agent. Based on the data and anecdata available to me, this strategy is working quite well, but YMMV.

Vercel Sandbox: ◾ Growing DAUs at 100% m/o/m ◾ 3.5M+ sandboxes created per day ◾ Best-in-class Active CPU pricing model ◾ Powering @notion, @airtable, @meta, @zapier, @coderabbitai, @interaction, @conductor_build, @blackboxai… 🐐 farm My DMs are open for migration help or if missing anything with: https://vercel.com/sandbox

Easy money (British pounds)

Some really cool usecases of Web Analytics API: ▪️ Ask your agent to correlate visitors, custom events (“purchase”, “checkout”), with the evolution of your deployments and performance ▪️ Build custom frontends, and plot this data alongside e.g.: Stripe’s and Resend’s

Vercel Agent is excellent for optimization questions. Ask it to optimize your build, performance, your bill.

The @agentmail team has been cooking. Tell your agent to 𝚟𝚎𝚛𝚌𝚎𝚕 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚊𝚐𝚎𝚗𝚝𝚖𝚊𝚒𝚕 – no signup, automatic setup and unified billing.

The two most popular http://eve.dev features so far have been: 1️⃣ The ease of use / filesystem API 2️⃣ Observability We’re doubling down on both!

Powerful building block for autonomous, self-optimizing websites and applications. Give agents the ability to set up and tune experiments with feature flags.

“Open-weight models ran 29% of gateway tokens, up from 11% in April”

Make the model a cog in a machine you own. ◾ AI SDK → open model API ◾ http://Eve.dev → open Agent API ◾ AI Gateway → open ZDR inference Startups and enterprises must own their data, evals, model choices, software layer. Don't outsource your brain.

Easy money (Swiss francs)

You can now import 💗Lovable apps to Vercel with zero config. Just import your Git repo. New Lovable apps are Nitro-backed, the standard runtime for the open web. Start in Lovable, grow on Vercel: AI development with no ceiling.

I love that @shadcn has managed to build the best UI infrastructure for agents and for humans. It's so so satisfying to play with the new typeset configurator.

Deep dive into how you can generate designs, prototypes, frontends, and full stack apps with your own design system in @v0. As models continue to get faster, v0 gets more magical.

It’s model release week. I suspect Meta Spark 1.1, Grok 4.5, and GLM 5.2 will significantly displace token market share. Most agentic tasks require reasonably high intelligence at fast speeds. It’s a good time to be using ▲ AI Gateway!

X is the arena. Always has been

AI will make all software Native. Uncompromising performance and platform affinity.

RT Elon Musk Try out Grok 4.5 in Vercel!

Grok 4.5 now available to all Vercel customers

RT Greg Brockman Sol for developing next.js:

The blissful sound of all the pieces of the agent stack clicking together. ht @nishimiya. This will power my personal productivity agents!

The filesystem is beautiful. Want your http://eve.dev agent to have GitHub powers? Define 𝚝𝚘𝚘𝚕𝚜/𝚐𝚒𝚝𝚑𝚞𝚋.𝚝𝚜 and export 𝚌𝚛𝚎𝚊𝚝𝚎𝙶𝚒𝚝𝚑𝚞𝚋𝚃𝚘𝚘𝚕𝚜(). Eve exists to shape an open ecosystem of pluggable models, skills, channels, and tools like this ↓

RT Pete Koomen In <2yrs @bekacru turned better auth into the #1 auth framework for typescript and one of the most popular and influential oss projects in the world. He’s a world-class developer with impeccable taste. It’s hard to imagine a better home for him and his work than @vercel, or a better mentor than @rauchg. Congrats to bereket and the @better_auth team!

Heavenly victory 🇦🇷

Welcome @bekacru to Vercel. It's a privilege to join forces with Bereket and Better Auth to further our Open SDK vision. Developers deserve better auth, to serve humans and agents, built in the open and with taste. That's what Bereket has accomplished. Congrats! 🇪🇹🇺🇸

Making the dev world a better place

Update: 🇪🇸 ESP - 🇦🇷 ARG final. The legendary Spanish team will avenge team USA with a decisive defeat of 🇧🇪.

🆒 eve evals itself with 𝚎𝚟𝚎 𝚎𝚟𝚊𝚕. Web frameworks made testing an ecosystem choice. e.g.: React didn’t ship with a built-in testing solution. For agents, evals are essential… thus we ship 𝚎𝚟𝚎 𝚎𝚟𝚊𝚕 out of the box. For your agents and eve’s own evolution.

The ultimate test for coding AI: is software as a whole getting better? Are companies shipping faster? Do you now have apps and games you couldn't even dream of before? Is the software you're getting bug-free? For me: my own ability to influence my productivity has radically increased. I feel a level of agency and autonomy I never had before. I'm free to create and execute. I can communicate a vision with my colleagues instantly. Personal software is real and a big win, I have a bunch of web tools and macOS apps I wrote just for myself. For Vercel: it's been amazing to see our CTO @cramforce bring novel software to life with swaths of agents. Genuinely useful software that's having an impact industry-wide emerged nearly autonomously (http://chat-sdk.dev, http://just-bash.dev, http://deepsec.sh). That's just an example. Our PM team ships software and fixes bugs. Our junior engineers and interns ship quality software at scale. On a personal note, AI at my fingertips, as CLI or v0, allows me to keep up with all the product updates. I can build demos, apps and benchmarks on top of @vercel as new products go out. But the ultimate jury is that people should love our products, expand their usage, refer their friends and colleagues to the platform. So far that tracks well, and it's the main metric I watch (and obviously we take token costs seriously, just like any other infrastructure spend… there isn't and has never been a proclamation to "tokenmaxxx").

🇺🇸 USA - 🇦🇷 ARG final you heard it here first

🏁 I animated the token 💰 spend race, from ~lifetime Vercel AI Gateway usage, which aggregates trillions of tokens from millions of developers a month. Fascinating to see the fluctuations among the labs, Anthropic's dominance, and the rise of open weight AI.

🟦⭐🟦⭐🟦🟥🟥🟥🟥🟥🟥 ⭐🟦⭐🟦⭐⬜⬜⬜⬜⬜⬜ 🟦⭐🟦⭐🟦🟥🟥🟥🟥🟥🟥 ⭐🟦⭐🟦⭐⬜⬜⬜⬜⬜⬜ 🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥 ⬜⬜⬜⬜⬜⬜⬜⬜⬜⬜⬜ 🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥 ⬜⬜⬜⬜⬜⬜⬜⬜⬜⬜⬜ 🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥🟥

Agentic self-improvement. Give your agent the ability to introspect its past runs, spot inefficiencies, errors, redundant tool calls, and produce new prompts and skills. That’s why agent observability is built-in when you deploy http://eve.dev to Vercel.

“We hold these truths to be self-evident, that all men are created equal, that they are endowed by their Creator with certain unalienable Rights, that among these are Life, Liberty and the pursuit of Happiness.” Such beautiful, sacred words.

I like my airplanes like I like my 𝚁𝚎𝚊𝚌𝚝.𝚌𝚛𝚎𝚊𝚝𝚎𝙴𝚕𝚎𝚖𝚎𝚗𝚝 syntax: JSX A glimmer of hope for how great airtravel could be again. Lightning quick onboarding, no security theater, Starlink, unstressed friendly staff, convenient terminals.

This is so powerful. ▲ Sandbox can now run 𝚍𝚘𝚌𝚔𝚎𝚛 and 𝚏𝚞𝚜𝚎, unconstrained. MicroVMs are the gift that keeps on giving. Instant boots, unconstrained runtimes. Very happy we bet on it as the foundation for 🌊 Fluid compute. S3-backed filesystem for agents in 10LOC ↓

Just learned our next baby will receive a special “Freedom 250” social security card for being born in the second half of this 250th anniversary year. Such a cool keepsake 🥹 🇺🇸 🦅

We've been explaining AI Gateway as a C̶o̶n̶t̶e̶n̶t̶ Token Delivery Network. Like a CDN for AI models. One great feature of CDNs is the ability to dynamically re-route or deny traffic without redeployment. When Fable was suddenly retired, we worried about production workloads depending on it. Even Fable aside, models get retired quite often as GPU capacity is heavily contested. Yet our data shows people still having happy production traffic of older model versions! We're solving this now with AI Gateway Rules. e.g.: you can now rewrite model "routes" on the fly! 𝚟𝚎𝚛𝚌𝚎𝚕 𝚊𝚒-𝚐𝚊𝚝𝚎𝚠𝚊𝚢 𝚛𝚞𝚕𝚎𝚜 𝚊𝚍𝚍 \ --𝚝𝚢𝚙𝚎 𝚛𝚎𝚠𝚛𝚒𝚝𝚎 \ --𝚜𝚘𝚞𝚛𝚌𝚎 𝚊𝚗𝚝𝚑𝚛𝚘𝚙𝚒𝚌/𝚌𝚕𝚊𝚞𝚍𝚎-𝚏𝚊𝚋𝚕𝚎-𝟻 \ --𝚍𝚎𝚜𝚝𝚒𝚗𝚊𝚝𝚒𝚘𝚗 𝚊𝚗𝚝𝚑𝚛𝚘𝚙𝚒𝚌/𝚌𝚕𝚊𝚞𝚍𝚎-𝚘𝚙𝚞𝚜-𝟻 This adds to the repertoire of capabilities and techniques AI Gateway brings to the table to recover lost tokens. If you drop tokens, you lose revenue and customers 💸 Kudos to @rtaneja_ @crowprose @shaper – we went from CLI design to production-grade capability very quickly!

Private connectivity between services is 🔑 for backends. 1️⃣ Register 𝚋𝚒𝚗𝚍𝚒𝚗𝚐𝚜 in 𝚟𝚎𝚛𝚌𝚎𝚕.𝚓𝚜𝚘𝚗 (1LOC) 2️⃣ Read it: 𝚗𝚎𝚠 𝚄𝚁𝙻("/𝚊𝚙𝚒", 𝚙𝚛𝚘𝚌𝚎𝚜𝚜.𝚎𝚗𝚟.𝙱𝙰𝙲𝙺𝙴𝙽𝙳_𝙸𝙽𝚃𝙴𝚁𝙽𝙰𝙻_𝚄𝚁𝙻) Works for Node, Python, 𝙳𝚘𝚌𝚔𝚎𝚛𝚏𝚒𝚕𝚎… you name it

Everyone in NYC has the same dog. It's a french bulldog. This needs to be studied

Watching our product owners pitch and demo internally with @v0⁠s feels like science fiction, especially with our design system fidelity. It gives the company end-user empathy and decision-making velocity that we never had with text or slides. Demos > memos.

Agents love to check their work before they push. You probably see it in the form of 𝚗𝚘𝚍𝚎 --𝚌𝚑𝚎𝚌𝚔, 𝚝𝚜𝚌 --𝚗𝚘𝙴𝚖𝚒𝚝, 𝚗𝚎𝚡𝚝 𝚋𝚞𝚒𝚕𝚍, etc all over your agent sessions. We’re now shipping the dry-run step for agentic deployments, minimizing costs and risk.

GLM is excellent at @nextjs. The evals validate it (http://nextjs.org/evals), my own vibes validate it, and @chamath’s http://8090.ai validates it

http://skills.sh is the new npm and the new github. Over time, you need fewer 'templates' and large piles of code. I haven't cloned a repo in a very long time. You need the instructions and best practices on how to build the best things.

Excited to partner with the best 🏎️

Content agents with http://eve.dev and @sanity_io. I recommend you ship the agent you can @ to fix docs, update website copy, draft a changelog or blog… it’s been a game changer for us internally.

At dinner, tech executive is relaying his company’s @vercel feedback, and then his 12-year-old son’s @vercel feedback 😁 Vercel is for everyone.

So great to get to work with @tobi and the wonderful @shopify team. Excited to push the agentic web forward.

Vercel Services You can now collocate e.g.: a Python backend API, an ExpressJS server, and a React SPA in one Vercel project. tl:dr; ▪️ You can run all locally with 𝚟𝚌 𝚍𝚎𝚟 ▪️ Deploy and rollback all at once ▪️ Observe, monitor, debug together ▪️ Internal networking

The time is now

curl -sN https://ascii-prisms.vercel.app by @_brian_zhang

RT Parker Conrad Grok Voice in Vercel!

Massive performance and memory usage improvements in @nextjs. Turbopack’s bet on the filesystem cache pays off greatly in a world of agents hammering 𝚗𝚎𝚡𝚝 𝚋𝚞𝚒𝚕𝚍.

Voice agents now on Vercel

So excited for the @vercel ships this week… some would say a decade in the making. any guesses?

RT Marc Andreessen 🇺🇸 Learn to ship.

You don't need a LinkedIn, you need a page on your website describing and linking to what you shipped

I now own http://rauch.com. Excited to give my children clean email handles. Domains are awesome. The internet is awesome.

Mythos / Sol cybersecurity capabilities are equally useful in an offensive as well a defensive capacity. If adversaries get ahold of an equivalent offensive capability, it poses a serious threat to US companies that remain unaware of latent vulnerabilities. In the meantime, I strongly recommend running deepsec[1] or similar harnesses with the available frontier models. [1] https://github.com/vercel-labs/deepsec

Me and my agents

Follow the 🌁

Human judgement in engineering is ironically even more crucial now. Deciding what to build. Deciding on the right architectures. Deciding whether you regenerate from scratch $$$ or reuse existing legos. Managing tech debt. You can do anything now, but you can't do everything.

Agents are particularly hard-to-debug software. For one, and by design, AI models behave in non-deterministic ways. Even two identical prompts don't always yield the same output. But agents are also complex distributed systems. They involve multiple steps of computation across functions and sandboxes, touching dozens of API services that can go down, rate limit you, etc. Nailing down observability out of the box for http://eve.dev on Vercel was a key priority for the team, and the feedback so far has been 🔥↓

The UI for AI is here. It's @shadcn

Next.js "Ways to fix this" with "Copy prompt" buttons is a work of (agentic) art

How we imbue coding agents with our design standards

Grok Imagine Video has become the clear leader in @vercel AI Gateway, now amounting to ~50% of videos generated by developers 🤯 http://vercel.com/ai-gateway/leaderboards/video/models

"Can @v0 use my design system?" you've asked. Now the answer is: @v0 can use the exact same components your product uses in prod. We put it to the test with @microsoft Fluent, @shopify Polaris, @ibm Carbon, @palantirtech Blueprint, @vercel Geist (ofc), and more. Watch ↓

Something that I love about working at @vercel is just how enjoyable it is to use our technology. From using the platform to ship new products, to the agents you find in our workspace that make life easier. It's like experiencing the future while building the future 🔁

Our best @aisdk release yet

AI will bring forth an unprecedented surge in entrepreneurship. From 'solopreneurs,' to the revitalization of the small & medium business segment, to the emergence of the largest companies of our times… providing the foundation of it all.

Really fast GLM now live

The data of tokens and uptime recovered by @vercel AI Gateway is truly astonishing

Starting an X Chat group for http://eve.dev feedback. If you’re deep into building an agent and have high quality critical feedback or requirements to share, DM me and I’ll add you to a group with eve engineers

Vercel + Cursor

Claude Design → Vercel, in one click

𝚆𝚎𝚋𝚂𝚘𝚌𝚔𝚎𝚝 (and 𝚜𝚘𝚌𝚔𝚎𝚝.𝚒𝚘) now supported on Vercel, from CDN to Fluid. Special full circle moment for @vercel

gm

It’s over for 🇦🇹. Sorry @timolins @tobiaslins. 🇦🇷 🇦🇷 🇦🇷

▲ + 🐡 Mythos-level intelligence on AI Gateway

The team cooked on http://vercel.com/home performance. 'Everything the light touches' was optimized Simba. Painting, layout, WebGPU shaders, blocking scripts. Every frame scrutinized. The best part is that we'll be updating our http://skills.sh with the lessons learned!

Coding agents will squeeze every ounce of IKEA effect out of you, if you let them.

Happy Father's Day. Thankful to my dad who spent every last penny on buying our family 'the bicycle of the mind'

Genuinely impressed, almost shocked, at how good GLM-5.2 by @zai_org is at coding. This changes things.

The next hot programming language is… markdown. A minimal eve agent: 📂 𝚊𝚐𝚎𝚗𝚝/ 📄 𝚒𝚗𝚜𝚝𝚛𝚞𝚌𝚝𝚒𝚘𝚗𝚜.𝚖𝚍 📂 𝚜𝚔𝚒𝚕𝚕𝚜/ 📄 𝚢𝚘𝚞𝚛-𝚎𝚡𝚙𝚎𝚛𝚝𝚒𝚜𝚎.𝚖𝚍 Deployable in one command: 𝚟𝚎𝚛𝚌𝚎𝚕. It’s the most accessible programming has ever been. And likely will ever be, at least for the generation of software fully defined and controlled by us humans. (As a fun fact, one of the initial prototypes for eve was codenamed 𝚕𝚊𝚜𝚝 by @timolins, both in homage to ‘@nextjs for agents’ but also in recognition of how enduring eve’s design feels to us.)

Agents are motivating so many healthy software habits. Open APIs, documentation (skills), tests (evals), Unix (CLIs), payment & commerce protocols, even wide 𝙰𝚌𝚌𝚎𝚙𝚝 use (markdown/json/html). The original vision of the WWW coming to life before our eyes.

Agents are motivating so many healthy software habits. Open APIs, documentation (skills), tests (evals), Unix (CLIs), payment & commerce protocols, even wide 𝙰𝚌𝚌𝚎𝚙𝚝-𝙴𝚗𝚌𝚘𝚍𝚒𝚗𝚐 use (markdown/json/html). The original vision of the WWW coming to life before our eyes.

http://vercel.com/design.md

(Part of) the wonderful team that made Vercel SHIP London possible 🫶

React → http://ai-sdk.dev Next.js → http://eve.dev @aisdk is more relevant than ever, given the intense model competition landscape. Just today, GLM 5.2, an open model, surpassed Opus 4.8 in our Next.js Evals (http://nextjs.org/evals) 🤯 But the world needs a practical solution for how to build and deploy agents. Just like React needed Next.js to solve the task of building an actual web application. And that's eve.

http://Eve.dev is Next.js for agents. I built Next with a simple premise: 𝚙𝚊𝚐𝚎𝚜/𝚒𝚗𝚍𝚎𝚡.𝚓𝚜 is all you need. Put some React in there and you’re good to go. Eve asks for even less. 𝚊𝚐𝚎𝚗𝚝/𝚒𝚗𝚜𝚝𝚛𝚞𝚌𝚝𝚒𝚘𝚗𝚜.𝚖𝚍. Put some English in there and you’re good to go. Like Next, it embraces the filesystem. You can guess what 𝚝𝚘𝚘𝚕𝚜/𝚚𝚞𝚎𝚛𝚢-𝚍𝚋.𝚝𝚜 does. An agent is just a directory, whose entire spec fits in the tweet below. And like Next on Vercel, it’s seamless to deploy. The infra, like Sandbox, Gateway, Workflow… is the output of your creation.

The hardest part of building an agent is not building the agent. It’s the data. It’s, ironically, figuring out OAuth, tokens, credentials, scopes… We have AGI sitting there, waiting to be unleashed. Vercel Connect solves for both security and ease of use. It’s delightful

RT Vercel Every agent needs streaming, models, durability, isolation, channels, and integrations. The Agent Stack has them all: ▪︎ AI SDK ▪︎ AI Gateway ▪︎ Workflow SDK ▪︎ Sandbox ▪︎ Chat SDK ▪︎ Vercel Connect 𝚎𝚟𝚎 implements them with one command ↓https://vercel.com/blog/agent-stack

It was so inspiring to chat with and learn from Will Shu, founder of Deliveroo. Few people have been in the arena day-in-and-day-out like him. Founder Mode before it had a name.