Vercel Developers✓

Vercel Daemons is now in public beta. Run background workers that pull jobs from queues, databases, or third-party systems.

Node.js 26 LTS is now available on Vercel. ▪︎ Default for all new projects ▪︎ HTTP/2 by default for built-in 𝚏𝚎𝚝𝚌𝚑 ▪︎ Temporal API for dates and time zones ▪︎ V8 14.6 JavaScript engine

You can now run @strix_ai's open-source pen testing tool with any of AI Gateway's 400+ models. One API key, zero markup.

Vercel Firewall now has separate controls for AI crawlers and assistants. You can block bots that collect content for AI training and still let AI assistants fetch your pages in response to user requests.

Vercel Plugin is now available in Antigravity. Turn your Antigravity agent into a Vercel expert, with skills for AI SDK, Vercel Functions, Workflow, and more.

You can now write routing middleware in Python. It runs before requests reach your app and can rewrite, redirect, or answer them. It works with FastAPI, Flask, Django, and other Python frameworks.

Vercel Agent can now investigate alerts before paging you. It checks logs and metrics to assess impact, then escalates only alerts it marks critical.

Your agent can now send feedback to Vercel. Use plain language to explain a bug or feature request, and your agent will use 𝚜𝚞𝚋𝚖𝚒𝚝_𝚏𝚎𝚎𝚍𝚋𝚊𝚌𝚔 via Vercel MCP to attach structured context and submit the comment.

Or send feedback from the terminal. The Vercel CLI now includes 𝚟𝚎𝚛𝚌𝚎𝚕 𝚏𝚎𝚎𝚍𝚋𝚊𝚌𝚔 for bugs, friction reports, and feature requests. Pipe in a file too: ▲ ~/ cat notes.txt | vercel feedback -

Paseo agents now run on Vercel Sandbox. • Install with one command • Control sessions from your phone • Use Pi, fx, Codex, Claude Code & more

Particle-1 is now available on AI Gateway. 𝚙𝚊𝚛𝚝𝚒𝚌𝚕𝚎/𝚙𝚊𝚛𝚝𝚒𝚌𝚕𝚎-𝟷 Post-trained on DeepSeek V4.1 Flash, it completes engineering tasks with fewer tokens. Use it to debug, plan code changes, and break down multi-step problems.

Vercel Observability now shows AI traffic. See which AI bots visit your site, how often, and what they request.

fx × T3 Code: our open-source agent harness, fx, is now a built-in provider in T3 Code. • Runs on web, desktop, and mobile • Works with your existing models and skills

fx v0.0.15 Less memory. Faster resumes. Smaller binary. - 70% less memory in long sessions - 7.66% smaller binary (6.15mib ← 6.66mib) - Image-heavy turn processing up to 3.3× faster - Session resumes about 18% faster - Automatic model catalog refresh - Fork conversations with /fork - Better image handling & crash recovery in libfx - Multiple bug fixes & security improvements

Your plain 𝙳𝚘𝚌𝚔𝚎𝚛𝚏𝚒𝚕𝚎 now deploys on Vercel. Add a 𝙳𝚘𝚌𝚔𝚎𝚛𝚏𝚒𝚕𝚎 or 𝙲𝚘𝚗𝚝𝚊𝚒𝚗𝚎𝚛𝚏𝚒𝚕𝚎 at your root, then Vercel selects the Container preset, builds it, and routes traffic to the image.

On average, Agent sessions in the dashboard and Slack cost 67% less. We rebuilt context management to use fewer tokens and improve prompt caching. Changes are live, with no action required.

Vercel × @ElevenLabs: 14 models on AI Gateway, 50% off through Nov 9. • Realtime voice agents • Music • Sound effects • Multi-voice dialogue • Streaming speech over WebSockets • Speech to text

You can now create custom monitors from Vercel Observability queries. • Track metrics like cost or error rate • Set threshold or anomaly-based alerts • Get notified via Slack, email, or webhooks

𝙷𝚊𝚛𝚗𝚎𝚜𝚜𝙰𝚐𝚎𝚗𝚝 now supports image input across every harness adapter. Pass images alongside text in the standard AI SDK message format, and each harness's underlying vision model handles the rest.

eMudhra Security Advisory: eight intermediate CA keys were recoverable, so anyone could mint a trusted cert for any site. Vercel no longer trusts those roots on builds, Functions, Sandbox, and Image Optimization. Managed runtimes need no action.

Project cards now show the metric you pick. • Web Analytics: visitors, page views, online count • Observability: alerts, error rates, CDN requests • Firewall: allowed and denied requests • Speed Insights: LCP, CLS, RES