---
name: Neon Blog
slug: neon-blog
type: feed
source_url: https://neon.com/blog
organization: Neon
organization_slug: neon
total_releases: 201
latest_date: 2026-04-16
last_updated: 2026-04-19
tracking_since: 2025-02-04
canonical: https://releases.sh/neon/neon-blog
organization_url: https://releases.sh/neon
---

<Summary type="rolling" window-days="90" release-count="25">
Neon shifted decisively toward agent-native infrastructure over the last quarter. The platform moved beyond serving traditional developer workflows to become a first-class primitive for AI agents—from Stripe Projects automating database provisioning mid-agent execution, to the Cursor plugin giving agents structured access to schemas and credentials, to the MCP server standard letting agents discover and interact with Neon across different tools. Alongside this, Neon doubled down on production readiness for agent-generated apps: branching for isolated testing, autoscaling reports for visibility, and Auth integration with Vercel previews so agents can scaffold full-stack systems without manual configuration. The company also shipped zero-downtime patching prewarming to keep databases available during infrastructure maintenance, and expanded into data lakehouses with zero-ETL tooling for Postgres workloads moving toward enterprise analytics.
</Summary>

<Summary type="monthly" period="March 2026" release-count="4">
Neon shipped features cementing its role in agentic AI workflows. Stripe Projects integration enabled AI coding agents to provision databases directly within generated applications, while a case study with Specific highlighted the platform's ability to spawn thousands of databases at scale for agent-managed infrastructure. Separately, zero-downtime patching entered its first phase with prewarming, and query cancellation behavior in psql received attention.
</Summary>

<Release date="April 16, 2026" published="2026-04-16T22:06:03.000Z" url="https://neon.com/blog/neon-codex-plugin">
## Neon is now available as an OpenAI Codex Plugin

An official Neon plugin is now available in the OpenAI Codex marketplace. It connects Codex directly to your Neon databases through MCP, so you can provision and manage Postgres databases without leaving your workflow. Once installed, Codex can interact with your Neon account, not just read static guidance about it. You can ask it to [&hellip;]
</Release>

<Release date="March 27, 2026" published="2026-03-27T14:04:17.000Z" url="https://neon.com/blog/prewarming">
## Zero-Downtime Patching Part 1: Prewarming

Ensuring customer databases are always available is one of the most important things we do in Neon and Lakebase. We’ve designed the system with redundancy at every level, automatically failing over and recovering your database in the event of hardware or software failures. In a large-scale system, such unplanned failures are a statistical expectation, but [&hellip;]
</Release>

<Release date="March 26, 2026" published="2026-03-26T16:14:37.000Z" url="https://neon.com/blog/neon-works-with-stripe-projects-for-agentic-provisioning">
## Neon works with Stripe Projects for agentic provisioning

<p>For most of 2025, AI coding agents got good at a specific thing: writing code. Give an agent a prompt, and it could scaffold an app, wire up an API, write migrations. But when the code was done, the agent stopped. Spinning up a real database, creating an account, getting credentials into the environment&#8230; that [&hellip;]</p>
</Release>

<Release date="March 18, 2026" published="2026-03-18T19:19:23.000Z" url="https://neon.com/blog/how-specific-provisions-thousands-of-databases-for-coding-agents-using-neon">
## How Specific Provisions Thousands of Databases for Coding Agents Using Neon

<p>&#8220;I&#8217;m genuinely surprised by how well it handles that scale. You can create tons of databases and they&#8217;re available immediately. You can branch out immediately. All of those things make it really nice for agent-managed infra.&#8221; Iman Radjavi, Co-founder, Specific.dev What Specific builds Specific (YC F25) is a cloud platform designed for coding agents. With [&hellip;]</p>
</Release>

<Release date="March 5, 2026" published="2026-03-05T16:32:34.000Z" url="https://neon.com/blog/ctrl-c-in-psql-gives-me-the-heebie-jeebies">
## Ctrl-C in psql gives me the heebie-jeebies

<p>There are a few different reasons to hit the brakes on a Postgres query. Maybe it’s taking too long to finish. Maybe you realised you forgot to create an index that will make it orders of magnitude quicker. Maybe there’s some reason the results are no longer needed. Or maybe you, or your LLM buddy, [&hellip;]</p>
</Release>

<Release date="February 26, 2026" published="2026-02-26T17:49:06.000Z" url="https://neon.com/blog/inside-qwikbuild-neon-powered-architecture">
## 15,000+ Apps Built Over WhatsApp: Inside QwikBuild’s Neon-Powered Architecture

<p>“The biggest strength of Neon is how it decouples storage and compute and makes them independently scalable. When an app isn’t being used, the compute node can be put in idle mode at extremely low cost, which lets us handle a wide range of scale and complexity without compromise.” (Nilesh Trivedi, co-founder and CTO at [&hellip;]</p>
</Release>

<Release date="February 25, 2026" published="2026-02-25T19:45:21.000Z" url="https://neon.com/blog/where-agents-meet-infrastructure-encore-leap-and-neon">
## Where Agents Meet Infrastructure: Encore, Leap, and Neon

<p>From the start, the team at Encore has been focused on solving a simple problem: shipping production infrastructure shouldn’t require a dedicated platform engineering team. They set out to make deploying real applications feel simple without abstracting away control; in Encore, devs can define infrastructure directly in Go or TypeScript, and the platform turns that [&hellip;]</p>
</Release>

<Release date="February 24, 2026" published="2026-02-24T17:14:34.000Z" url="https://neon.com/blog/building-a-deep-research-agent-with-neon-and-durable-endpoints">
## Building a Deep Research Agent with Neon and Durable Endpoints

<p>Every AI lab is shipping research agents. OpenAI&#8217;s Deep Research, Perplexity, and Gemini&#8217;s research mode. These products are not simple RAG pipelines. Recent papers like DeepResearcher and Step-DeepResearch formalize what makes them work: a recursive loop of planning, searching, learning, and reflecting, where the agent decides when to go deeper and when to stop. The [&hellip;]</p>
</Release>

<Release date="February 17, 2026" published="2026-02-17T18:58:33.000Z" url="https://neon.com/blog/neon-is-a-cursor-plugin">
## Neon Is a Cursor Plugin

Cursor just launched plugins, making it easier than ever to give Cursor structured access to external tools and infrastructure. Neon is part of the initial launch set: you can install the Neon plugin today from the Cursor Marketplace to give Cursor live access to your Neon organization along with the knowledge it needs to be [&hellip;]
</Release>

<Release date="February 12, 2026" published="2026-02-12T19:57:38.000Z" url="https://neon.com/blog/autoscaling-report-2025">
## Neon Compute Autoscaling Report

View the Autoscaling Report here.
</Release>

<Release date="February 10, 2026" published="2026-02-10T19:47:14.000Z" url="https://neon.com/blog/add-mcp">
## add-mcp: Install MCP Servers Across Coding Agents and Editors

A few weeks ago, Vercel released add-skill (now npx skills), a CLI for installing agent skills across different coding agents and editors like Claude Code, Cursor, and VS Code. It solves a very real problem: each tool looks for agent skills in a different place, which makes setup repetitive and documentation painful to maintain. The [&hellip;]
</Release>

<Release date="February 6, 2026" published="2026-02-06T20:56:25.000Z" url="https://neon.com/blog/how-zite-provisions-isolated-postgres-databases-for-every-user">
## How Zite Provisions Isolated Postgres Databases for Every User

“We were getting ready to hire dedicated engineers just to manage and scale Zite Database. With Neon, we didn’t need to do that – we were able to give every end user their own database, including on the free plan” (Dominic Whyte, Co-founder at Zite) Zite is an AI-native app builder for the kind of [&hellip;]
</Release>

<Release date="February 6, 2026" published="2026-02-06T20:45:28.000Z" url="https://neon.com/blog/the-new-v0-is-ready-for-production-apps-and-agents">
## The New v0 Is Ready for Production Apps and Agents

v0 just went through a big rebuild. What started as a fast way to explore ideas has now evolved into a platform designed to ship real, production-ready software, not just quick demos or one-off prototypes. v0 is no longer about generating code – it’s about helping teams ship. With this release, v0 moves beyond UI [&hellip;]
</Release>

<Release date="February 2, 2026" published="2026-02-02T17:10:46.000Z" url="https://neon.com/blog/agentuity-a-cloud-where-agents-can-actually-build">
## Agentuity: A Cloud Where Agents Can Actually Build

“Agents don’t want heavyweight infrastructure that lives forever, they want primitives they can spin up, use, and discard as part of their work. Neon fits that model perfectly: it behaves the way agents actually think about state” (Rick Blalock, Co-founder at Agentuity) Existing cloud infrastructure is built around the software model developers have used for [&hellip;]
</Release>

<Release date="January 29, 2026" published="2026-01-29T17:31:27.000Z" url="https://neon.com/blog/behind-modem-dev-product-velocity">
## Behind Modem.dev’s Product Velocity

“Neon branching fundamentally accelerates our developer experience. It’s a huge reason we’re able to ship faster without worrying about breaking things” (Ben Vinegar, Co-founder at Modem) If you’re a PM or even an engineer at a small startup, this will hit home: This is the pain that Modem is set to solve. From Noisy Conversations [&hellip;]
</Release>

<Release date="January 23, 2026" published="2026-01-23T17:00:37.000Z" url="https://neon.com/blog/the-neon-vs-code-extension-just-got-a-big-update">
## The Neon VS Code Extension Just Got a Big Update

If you’ve a VS Code user, you might remember the Neon extension under its earlier name, Neon Local Connect. We recently shipped an update for the extension with much more complete functionality: it now understands the repository you have open, detects real Neon connection strings in your project, and lets you connect to the corresponding [&hellip;]
</Release>

<Release date="January 22, 2026" published="2026-01-22T18:13:30.000Z" url="https://neon.com/blog/agent-skills-in-2026">
## Agent Skills in 2026

2026 is starting off hot, and skills are suddenly everywhere. The Agent Skills spec is now supported across all major coding agents and increasingly adopted by developer tools, including Neon. But let’s start from the beginning. The origins of agent skills The concept of agent skills didn’t arrive fully formed: What agent skills are (and [&hellip;]
</Release>

<Release date="January 21, 2026" published="2026-01-21T18:38:58.000Z" url="https://neon.com/blog/meet-fimo-ai-the-ai-native-cms-from-strapi">
## Meet Fimo.ai, the AI-Native CMS from Strapi

“Fimo lets teams experiment without fear because you can always roll back. Neon’s branches and snapshots are what make that possible” Pierre Burgy, CEO at Strapi The good folks at Strapi just launched something exciting: Fimo.ai, an AI-native CMS built specifically for real websites. This team has experience (and opinions!) when it comes to building [&hellip;]
</Release>

<Release date="January 20, 2026" published="2026-01-20T17:17:15.000Z" url="https://neon.com/blog/building-tanstack-com-with-neon-and-tanstack-duh">
## Building TanStack.com with Neon and TanStack (duh)

“Neon was so easy to get started, and it worked flawlessly with TanStack Start and TanStack Query. When you start a new project with TanStack Start and select Neon in the CLI, you get a working database instantly and later you can go claim it, which is one of the coolest things I’ve seen” (Tanner [&hellip;]
</Release>

<Release date="January 19, 2026" published="2026-01-19T17:43:45.000Z" url="https://neon.com/blog/auth-that-just-works-in-vercel-previews">
## Auth That Just Works in Vercel Previews

If you’re integrating your Vercel preview deployments with Neon, you’re already getting an isolated Postgres branch per preview. We just extended the same automation to authentication. When you use Neon through the Vercel integration and enable Auth, every Vercel deployment gets its own isolated authentication endpoint, with URLs injected automatically and trusted domains already configured [&hellip;]
</Release>

<Pagination page="1" total-pages="11" total-items="201" next="https://releases.sh/neon/neon-blog.md?page=2" />