Knowledge catalogue
Protected Source Maps is a Vercel feature that enables developers to securely ship browser source maps to production without exposing them publicly. This allows for proper error tracking and debugging
Vercel introduced a trusted sources feature for deployment protection that allows teams to control which sources can trigger deployments, enhancing security by restricting deployment access to verifie
A security update for Next.js released in May 2026 by Vercel addressing identified vulnerabilities in the framework. The release likely includes patches for security issues affecting Next.js applicati
This Vercel feature automatically adds Git committers to a team workspace based on their commit activity, streamlining team collaboration by eliminating manual member invitations. The auto-add functio
Vercel introduced a security feature allowing marketplace credentials to be restricted to production-only access, preventing their use in development or preview environments. This enhancement helps pr
Deepsec is a security tool introduced by Vercel designed to identify and help remediate vulnerabilities within codebases. The tool functions as a security harness that automates vulnerability detectio
Native Deployment Checks can now be run on every Vercel deployment, processing linting and typechecking in parallel with the build process. These built-in checks integrate with existing integrations (
This year's AI Accelerator winners shipped agents for finance teams, application security, and real estate. They built with $8M in credits and hands-on mentorship from Vercel, @awscloud, @OpenAI, @Ant
Vercel has updated its default deployment retention policy for hobby tier projects to automatically retain deployments for 30 days. This change simplifies deployment management for free-tier users by
Sergiu Gatlan / BleepingComputer: Have I Been Pwned: ShinyHunters' breach of ADT exposed the personal data of 5.5M people; ADT previously disclosed data breaches in August 2024 and October 2024 — The
Google's Gemma 4 models — the 26B (Mixture of Experts) and 31B (Dense) variants — are now available on Vercel AI Gateway. Built on the same architecture as Gemini 3, both open models support functi...
Waldium is a YC-backed, two-person agentic CMS that automates content research and creation, and gives every customer blog its own Model Context Protocol (MCP) server endpoint so AI agents can quer...
Vercel AI Gateway is a unified API product that provides access to hundreds of AI models from major providers — including OpenAI, Anthropic, Google, xAI, and others — through a single endpoint, eli...
MiniMax M2.7 is now available on Vercel AI Gateway in two variants: standard and high-speed, accessible without requiring separate provider accounts. It represents a significant improvement over pr...
Alibaba's Qwen 3.6 Plus is now available on Vercel's AI Gateway, accessible via a unified API with no additional provider accounts required. Compared to Qwen 3.5 Plus, this model adds stronger age...
Vercel now supports building Model Context Protocol (MCP) servers directly within Nuxt applications via the Nuxt MCP Toolkit (`@nuxtjs/mcp-toolkit`), which exposes app features — including tools wi...
Vercel's Chat SDK now supports Liveblocks, enabling bots to read and respond within Liveblocks Comments threads via a new Liveblocks adapter. This is an official vendor adapter built and maintained...
Vercel's Chat SDK has added support for Zernio, a unified social media API, via a new official adapter built and maintained by the Zernio team. Using this adapter, teams can build bots that operate...
Vercel Enterprise team owners can now set a default build machine at the team level, streamlining configuration across their organization. This setting automatically applies to all newly created pr...
GLM 5.1 from Z.ai is now available on Vercel's AI Gateway with no markup and no separate provider account required. Designed for long-horizon autonomous tasks, it handles planning, execution, testi...
Vercel's AI builder v0 has acquired the team behind new.website, a tool founded to make creating beautiful, production-ready websites effortless through built-in primitives like forms, databases, S...
Vercel AI Gateway now supports Fast Mode for Claude Opus 4.6, an early experimental feature that delivers 2.5x faster output token speeds while maintaining the same model intelligence. It is partic...
CVE-2026-23869 is a high-severity Denial of Service vulnerability affecting React Server Components. It can lead to Denial of Service and is present in Next.js 13.x, 14.x, 15.x, and 16.x, impactin...
Vercel's AI Gateway now supports xAI's Grok 4.20 model family, including variants for multi-agent, reasoning (beta), and non-reasoning use cases, accessible without requiring a separate provider ac...
Leonardo.AI and Relevance AI — two Australian AI-native startups — operate at global scale (processing millions of images daily and running autonomous agents across time zones, respectively) withou...
Vercel's Custom Reporting API for AI Gateway, now in beta for Pro and Enterprise plans, provides programmatic access to cost, token usage, and request volume across all AI Gateway traffic — includi...
The AI Gateway now provides robust, centralized controls for data governance, enabling team-wide and request-level enforcement of Zero Data Retention (ZDR) and prompt training opt-outs. By integrat...
Durable is an AI-powered business builder that helps entrepreneurs launch and manage businesses in minutes, serving more than 3 million businesses with a team of just 6 engineers and no DevOps st...
Agent-generated code enhances development speed but introduces new risks because agents lack awareness of a production environment's real-world constraints (e.g., traffic patterns, capacity, or fai...
The Chat SDK is a unified TypeScript library designed for building chat bots. This tool allows developers to maintain a single codebase to create chatbots that reliably function across multiple pla...
The Chat SDK has been updated to support concurrent message handling. This feature allows developers to control the processing of newly arrived messages relative to those already being handled, ens...
The Chat SDK now enables developers to schedule Slack messages for future delivery. This functionality utilizes `thread.schedule()` by passing both the desired message content and a specific `postA...
Inception has launched Mercury 2, a model providing reasoning-grade quality with low, real-time latency, making it suitable for complex applications like agentic loops, coding assistants, and RAG p...
This AI Gateway enforces zero data retention policies, ensuring sensitive information is not stored after processing and preventing third-party AI providers from using your data for training. The p...
Jev was adopted faster than any other AI model in the history of AI Gateway, achieving roughly 13 % of total team adoption on its first day. This rate represented twice the uptake of the GPT‑5.6 famil
Natural language can act as an in-context control surface that streams rich, constrained UI and links users into deeper web views.
Auto-generated index of all tools mentioned across the wiki.
Ora runs agents on live websites and traces every step. When a signup, integration, or payment stalls, teams see which step, what the agent tried, and what to change. The whole platform is built on Ve
DeepSeek is increasing its presence in the AI inference market by competing for higher token volumes, while Anthropic maintains its leadership position in terms of overall spending. This analysis like
This article discusses security measures and best practices for protecting AI model inference endpoints from unauthorized access and theft, likely covering topics such as API authentication, rate limi
The Nuxt MCP Toolkit has been updated to support MCP apps, expanding its capabilities for developers working with Nuxt and Model Context Protocol applications. This enhancement likely enables better i
Additional security bulletin updates include: • Clarification that account and project deletion do not eliminate environment variable risk • Guidance on multi-factor authentication • Product updates t
Our investigation has revealed that the incident originated from a third-party AI tool with hundreds of users whose Google Workspace OAuth app was compromised. We recommend that Google Workspace Admin
Our investigation is ongoing. In the meantime, we have updated the security bulletin with best practices you can follow for peace of mind: https://vercel.com/kb/bulletin/vercel-april-2026-security-inc
We built a software factory for AI SDK. Each step is an agent, and humans merge changes. Four weeks in: ▪️ The factory authors up to 35% of merged PRs ▪️ It closed 70% of issues in July ▪️ Open bugs a
Introducing Agent Plugins, an open standard for extending agents. Supports Agent Skills and MCP, with more to come. Built in collaboration with: @awsdevelopers, @code, @cursor_ai, @github, and @openai
Eve's Chat SDK now supports multiple adapter options, allowing developers to integrate various chat platforms and services without being locked into a single solution. This flexibility enables teams t
We are rebuilding Hydrogen from the ground up with @Shopify. It's agent-first, runtime-agnostic, and runs anywhere JavaScript does. Learn more and try the Next.js developer preview ↓ https://vercel.co
AI SDK 7 is here. This release sets the foundation for agents and AI platforms in production: approvals, durability, telemetry, and more. AI SDK 7 is now available. Introducing: reasoning control, age
Decouple deploy from release. { 𝚒𝚜𝙴𝚗𝚊𝚋𝚕𝚎𝚍 ? <𝙽𝚎𝚠𝙳𝚊𝚜𝚑𝚋𝚘𝚊𝚛𝚍 /> : <𝙾𝚕𝚍𝙳𝚊𝚜𝚑𝚋𝚘𝚊𝚛𝚍 /> } 🔗 Merge code when it's ready. 🎚️ Flip a flag when the feature is. https://vercel.com/blog/vercel-flags-platform-native
We're closing out SHIP LDN with @rauchg and @HarryStebbings for an exclusive fireside chat on building, backing, and what's next. Sign up for your spot on the waitlist today: https://vercel.com/ship/l
A prompt can cost a million times more than an HTTP request, so token theft is a high-margin business for attackers. How we protect our AI endpoints ↓ https://vercel.com/blog/protecting-against-token-
Agents, agents, agents at Ship London 🇬🇧 ▪︎ Video agents with @GoogleDeepMind ▪︎ Real-time voice agents with @ElevenLabs ▪︎ Agents in production with @Telegraph, @currys, @AKQA, and @easyJet June 17 a
AI Gateway now supports team-wide Zero Data Retention (ZDR). Building safely with multiple AI models means wrestling with fragmented data policies, per-provider negotiations, and the hope that develop
Automated lint: 19 errors, 64915 warnings, 3 info
We’re extending free Kimi K2.6 usage through Nous Portal until midnight PT tonight! What will you build? Kimi K2.6 is free on Nous Portal for the next 24 hours Made possible by @vercel's AI Gateway &
Cursor allows users to customize the CLI status bar through the /statusline command to display personalized session and runtime information. This feature enables developers to configure which signals
Now you understand why Dario is panicking. Only a fool would join his planned $2 trillion IPO. Looks like today may be a record day for token volume % of open models on Vercel AI Gateway: 🟦 Open 78.4%
January 2025 I made the switch from OpenAI to Claude. It was awesome. No more annoying GPT Chats, I dove into the wonderful world of Claude Code, learned vibe coding with Github, Vercel on Next.js. Wa
Today, we also open the door to Fireworks Lab: Embed forward-deployed researchers and engineers to co-design or build your model for you. Join leaders like @cursor_ai, @harvey, @figma, @vercel, @cogni