Vercel

Coding agents want 𝚎𝚟𝚊𝚕. Today they get 𝚛𝚞𝚗: • Hardened QuickJS sandbox • Expose only approved host functions • Pause for human approval, then resume • Runs anywhere Node.js runs vercel.com/blog/introd...

Vercel Agent can now join Slack with the full production context of your apps and agents. ▪︎ Add @𝚟𝚎𝚛𝚌𝚎𝚕 to any thread ▪︎ Create plans and PRs ▪︎ Roll back deploys and update configs vercel.com/blog/introd...

We migrated the database behind every build at Vercel, one of our most critical services, while it handled 6,000 deployments a minute. The story of how it happened, our philosophy, and what we learned ↓ vercel.com/blog/how-we...

We're making our Sandbox Egress Firewall free on every plan. Vercel Sandbox goes beyond compute isolation. Recent security research shows why: untrusted code must be contained at the network boundary, not just the runtime. vercel.com/blog/a-sand...

Next.js 16.3 applications on Vercel send 45% fewer prefetch requests, 17% fewer static assets, and have 2x faster path metadata serving. Learn more ↓ vercel.com/blog/vercel...

Vercel Passport is now generally available for Enterprise customers. • Protect projects with your native IdP • Use verified identities across apps • Monitor access and create bypasses vercel.com/changelog/v...

Vercel Services gives your full stack app atomic deployment and rollback, a single preview URL, and a private network between services. One Vercel project for your entire application ↓ vercel.com/blog/vercel...

You can now run any Dockerfile on Vercel. # 𝙳𝚘𝚌𝚔𝚎𝚛𝚏𝚒𝚕𝚎.𝚟𝚎𝚛𝚌𝚎𝚕 𝙵𝚁𝙾𝙼 𝚐𝚘𝚕𝚊𝚗𝚐:𝟷.𝟸𝟺 𝙲𝙾𝙿𝚈 . . 𝚁𝚄𝙽 𝚐𝚘 𝚋𝚞𝚒𝚕𝚍 -𝚘 /𝚜𝚎𝚛𝚟𝚎𝚛 . 𝙲𝙼𝙳 ["/𝚜𝚎𝚛𝚟𝚎𝚛"] vercel.com/blog/docker...

Decouple deploy from release. { 𝚒𝚜𝙴𝚗𝚊𝚋𝚕𝚎𝚍 ? <𝙽𝚎𝚠𝙳𝚊𝚜𝚑𝚋𝚘𝚊𝚛𝚍 /> : <𝙾𝚕𝚍𝙳𝚊𝚜𝚑𝚋𝚘𝚊𝚛𝚍 /> } 🔗 Merge code when it's ready. 🎚️ Flip a flag when the feature is. vercel.com/blog/vercel...

We run 100+ agents in production. Deploying them was easy, making them secure at scale wasn't. So we built Vercel for Enterprise Apps and Agents. It's the DX you love, with identity, access, and audit trails built in. vercel.com/blog/vercel...

Introducing eve, an agent framework. 𝚊𝚐𝚎𝚗𝚝/ 𝚊𝚐𝚎𝚗𝚝.𝚝𝚜 𝚒𝚗𝚜𝚝𝚛𝚞𝚌𝚝𝚒𝚘𝚗𝚜.𝚖𝚍 𝚝𝚘𝚘𝚕𝚜/ 𝚜𝚔𝚒𝚕𝚕𝚜/ 𝚜𝚊𝚗𝚍𝚋𝚘𝚡/ 𝚜𝚌𝚑𝚎𝚍𝚞𝚕𝚎𝚜/ Like Next.js, for agents. vercel.com/blog/introd...

Vercel Connect makes accessing external data and systems simple and secure. It gives your apps and agents short-lived tokens with precise scopes. vercel.com/blog/introd...

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 ↓vercel.com/blog/agent-...

Vercel Workflows is GA. Your code is the orchestrator. Ship agents, backends, or any long-running process without managing queues, retries, or workers. vercel.com/blog/a-new-...

In 3 months, weekly deployments on Vercel have doubled. 30% are triggered by agents (up 1000% in 6 months). Agents are writing software that uses AI, and agents are building agents. Infrastructure must become agentic itself. That's what we're building. vercel.com/blog/agenti...

Sanity is now available on Vercel Marketplace. Connect your CMS in seconds and ship content-driven sites, apps, and agents with integrated billing and no setup overhead. vercel.com/changelog/s...

We're experimenting with ways to keep AI agents in sync with the exact framework versions in your projects. Skills, 𝙲𝙻𝙰𝚄𝙳𝙴.𝚖𝚍, and more. But one approach scored 100% on our Next.js evals: vercel.com/blog/agents...

We just released 𝚛𝚎𝚊𝚌𝚝-𝚋𝚎𝚜𝚝-𝚙𝚛𝚊𝚌𝚝𝚒𝚌𝚎𝚜, a repo for coding agents. React performance rules and evals to catch regressions, like accidental waterfalls and growing client bundles. How we collected them and how to install the skill ↓ vercel.com/blog/introd...

AI video generation and editing is powerful, but can take time. And when something fails, you lose the work you already paid for. Mux shipped @𝚖𝚞𝚡/𝚊𝚒 with Workflow DevKit so your code resumes from where it left off, instead of starting over. vercel.com/blog/how-mu...

We improved our text-to-SQL agent by removing 80% of its tools and adding a sandbox. 40% fewer tokens, 40% fewer steps, 3.5x faster. Read about our initial build, mistakes, and file system agent success. vercel.com/blog/we-rem...

Open-source AI, protected. Nous Research used BotID to stop inference abuse and reduce costs on their AI workloads. vercel.com/blog/how-no...

Save your holiday traffic for customers, not bots. Enterprise and Pro teams can use Vercel BotID Deep Analysis free of charge through January 15. vercel.com/changelog/f...

A 500% traffic spike from a bot network appearing for the first time with legitimate fingerprints and coordinated proxy rotation. BotID Deep Analysis adapted in real-time and blocked it automatically within 5 minutes. vercel.com/blog/botid-...

Vercel Agent has a new skill: incident response. It can now intelligently investigate anomalies to surface critical issues and speed up time to resolution. New Agent users can claim a $100 free credit. vercel.com/blog/vercel...

You can ship native Next.js inside ChatGPT. Build productivity tools, e-commerce apps, or even games like Doom in ChatGPT with our starter template. Read our deep dive on how we made this possible. vercel.com/blog/runnin...

Open source server rendering benchmarks show architecture matters. Fluid compute: 1.2-5x faster across Next.js, React, SvelteKit, and more. vercel.com/blog/fluid-...

One of the world's largest financial institutions introduced BotID's invisible CAPTCHA to mitigate increased bot traffic. Learn how BotID helped them uncover, identify, and disarm a major SEO poisoning attack: vercel.com/blog/botid-...

We’ve made all CDN serving on Vercel 10% faster (P75), while reducing memory by 15%. Learn the behind the scenes of applying Bloom filters to this problem, while serving 1T monthly requests. vercel.com/blog/how-we...

Cold starts are the Achilles' heel of serverless. Fluid fixes that. Learn how Vercel achieves a sub-0.6% cold start rate automatically through platform optimizations. vercel.com/blog/scale-...

Agents that load dynamic MCP tools risk security and quality issues: • Prompt injection • Unreliable tool calls • Unexpected changes • Wasted tokens 𝚖𝚌𝚙-𝚝𝚘-𝚊𝚒-𝚜𝚍𝚔 generates static tools you control so they stay stable and predictable. vercel.com/blog/genera...

Billions of requests across MCP servers deployed on Vercel, including Zapier, Solana, and our own. A key insight: wrapping your API in an MCP server isn't enough. Here's what's working best so far: vercel.com/blog/the-se...

Introducing a more flexible Pro plan for modern teams and AI workloads. • Credit-based usage model • Free viewer seats • Self-serve enterprise features • Spend management by default Available starting today → vercel.com/blog/new-pr...

At Vercel, our relationship with open source is foundational. Today we're sharing our Open SDK strategy, which is a commitment you can hold us to. vercel.com/blog/open-s...

We recently ran a successful live failover of our control plane database from Azure West US to East US 2. Our goal was to validate that Vercel can survive a complete regional failure of its core database. Here's the full breakdown: vercel.com/blog/prepar...

Vercel AI Gateway is now generally available. • Access hundreds of models • Zero markup on tokens (including BYOK) • No provider accounts needed • High rate limits • Failover for high reliability • Sub-20ms latency • AI SDK and OpenAI-compatible vercel.fyi/ai-gateway

There’s a myth that serverless compute requires more database connections. We bust that myth, but reveal a real problem, and share our solution. vercel.com/blog/the-re...

Our official Vercel MCP server is now live. AI clients like Claude and VS Code with Copilot can now read Vercel docs and securely access your projects, deployment logs, and more using OAuth with read-only permissions. vercel.com/blog/introd...