Vercel Programming Tutorials & Engineering Articles

Agent Plugins 1.0.0 is a new, vendor-neutral directory specification—backed by Google, Amazon, Microsoft, and others—for packaging Agent Skills and MCP servers into a single portable unit. By standardizing the manifest (plugin.json) and utilizing a fixed directory layout, it eliminates the need for developers to maintain separate wrappers or configurations to support different AI coding agents and IDEs. Google has officially joined as a Core Maintainer and already rolled out support in the Agents CLI and Data Agent Kit, allowing developers to start building and distributing interoperable plugins today.

ClickHouse is joining the Open Secure AI Alliance alongside NVIDIA and other industry leaders to help build open tools that keep AI agents secure.

This post shows a lightweight metrics layer for ClickHouse using MooseStack, an open source developer agent harness for ClickHouse.

A Solutions Architect’s experience building a retail analytics platform with AI agents, real-time dashboards, and full observability on the ClickHouse data platform

We've released @clickhouse/rowbinary a Node.js reader and writer for ClickHouse's RowBinary formats. You can import it and call its generic parser like any other library. But it also ships as an Agent Skill: point a coding agent at the bundled `SKILL.md`

The open-source Genkit framework has introduced the Agents API, a full-stack tool designed to simplify the complex plumbing of conversational AI by packaging message history, tool loops, and streaming into a single interface. The API supports flexible, server- or client-managed state persistence—allowing for advanced workflows like history branching, long-running detached tasks, and multi-agent coordination—while seamlessly connecting backends to frontends via a unified wire protocol. Currently available in preview for TypeScript and Go, it also integrates with the Genkit Developer UI to allow developers to easily test, debug, and inspect agent snapshots without writing client code.

When building with agents, most guides will give you the happy path - how to do something the best way, without friction. This post is all friction, and how to get through it when things go wrong.

Building a GitHub traffic dashboard with Stripe Projects revealed a surprising shift from “AI coding” into real infrastructure orchestration. In under an hour, Auth0, Supabase, Vercel, Prisma, deployments, environments, and scheduled jobs materialized around an idea with remarkable speed. The experience highlighted both the power and the emerging challenge of AI-assisted infrastructure: operational visibility, ownership clarity, environment management, and understanding rapidly orchestrated systems.

This post is a follow-up to last week’s “From init to deploy: building with agents and Stripe Projects” and explores the learnings gained along the way.

Stripe Projects makes it easy to spin up a useful, complex application that uses various SaaS providers. This post describes how one of our developer advocates built an internal transcript editing application using Stripe Projects, Vercel, and OpenRouter.

By Brian Yu and Ashwin Nathan, Members of the Technical Staff

A2UI v0.9 introduces a framework-agnostic standard designed to help AI agents generate real-time, tailored UI widgets using a company’s existing design system. This update simplifies the developer experience with a new Agent SDK for Python, a shared web-core library, and official support for renderers like React, Flutter, and Angular. By decoupling UI intent from specific platforms, the release enables seamless, low-latency streaming of generative interfaces across web and mobile applications. Integrating with broader ecosystems like AG2 and Vercel, A2UI v0.9 aims to move generative UI from experimental demos to production-ready digital products.

Provision hosting, databases, auth, analytics, AI and other dev tools from the Stripe CLI. Stripe Projects creates real resources in your own provider accounts, securely syncs agent-ready credentials, supports upgrades to paid tiers, and handles payments without leaving the terminal.

To bridge the gap between static model knowledge and rapidly evolving software practices, Google DeepMind developed a "Gemini API developer skill" that provides agents with live documentation and SDK guidance. Evaluation results show a massive performance boost, with the gemini-3.1-pro-preview model jumping from a 28.2% to a 96.6% success rate when equipped with the skill. This lightweight approach demonstrates how giving models strong reasoning capabilities and access to a "source of truth" can effectively eliminate outdated coding patterns.

The article discusses the new plugin support in Cursor, enabling users to connect agents to external tools and enhance their functionality throughout the product development lifecycle.

The article introduces A2UI, an open-source project designed for agent-driven interfaces that allows agents to generate contextually relevant user interfaces.

The article discusses the advancements in AI agents with the introduction of Gemini 3 Pro Preview, highlighting its capabilities for building sophisticated agents using open-source frameworks.

The article discusses the CPU performance benchmarks of Cloudflare Workers compared to Vercel, revealing initial discrepancies and subsequent improvements made to enhance performance.

The article announces the establishment of the React Foundation, which will oversee the governance and development of React and React Native, ensuring a vendor-neutral environment for the community.

This article serves as a practical guide for building ClickHouse-powered APIs in web applications, specifically using React and MooseStack.

This article discusses how to instrument a Next. js application using OpenTelemetry and ClickStack, focusing on the integration of observability and analytics through ClickHouse.

The article discusses MorphLLM, an innovative solution for AI agent builders that addresses the inefficiencies of traditional code editing methods.

This article discusses how Cloudflare is enhancing its platform for building AI agents, introducing new tools and frameworks that simplify the development process.

The article announces the recipients of the 2024 Spotify FOSS Fund, which supports open source projects.

The article discusses how to integrate payments into workflows utilizing Large Language Models (LLMs) and function calling, specifically through the Stripe agent toolkit.

Cloudflare celebrated its 13th birthday with a series of announcements aimed at enhancing its services for customers and the broader internet community.

The article introduces a new Socket API designed for interoperability across JavaScript runtimes, specifically highlighting the connect() function.

LiteFS Cloud is a new service from Fly. io that provides managed backups and point-in-time restores for LiteFS, a distributed SQLite database.

The article discusses the launch of Redis by Upstash on Fly. io, highlighting its global scalability, low-latency capabilities, and integration with Fly. io's infrastructure.

Cloudflare has announced the first cohort of startups participating in the Workers Launchpad program, which has expanded to a total funding potential of $2 billion through partnerships with 40 VC f...

The article discusses the integration of Next. js Edge Runtime with Cloudflare Pages, marking it as the fourth full-stack framework supported by the platform.

The article discusses the development of Oxygen, a hosting solution for Hydrogen custom storefronts that integrates seamlessly with the Shopify ecosystem.

Cloudflare, in collaboration with Vercel, Shopify, and contributors from Node. js and Deno, has launched the Web-interoperable Runtimes Community Group (WinterCG).

The article discusses Notion's migration of its marketing site to Next.

The article discusses the development of Hydrogen, a React framework designed for building custom storefronts on Shopify.