<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/openai-and-four-rivals-just-agreed-on-one-standard-for-ai-agents-ruwl1ozkg" -->

---
title: OpenAI and four rivals just agreed on one standard for...
description: OpenAI, Amazon, Microsoft, Cursor (Anysphere), and Vercel have jointly published Agent Plugins, an open standard that lets a single agent extension work across...
canonical: https://daily.dev/posts/openai-and-four-rivals-just-agreed-on-one-standard-for-ai-agents-ruwl1ozkg
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: OpenAI and four rivals just agreed on one standard for AI agents | daily.dev
og:description: OpenAI, Amazon, Microsoft, Cursor (Anysphere), and Vercel have jointly published Agent Plugins, an open standard that lets a single agent extension work across...
og:url: https://daily.dev/posts/openai-and-four-rivals-just-agreed-on-one-standard-for-ai-agents-ruwl1ozkg
og:image: https://api.daily.dev/og/posts/ruWl1ozKG.png
og:image:alt: OpenAI and four rivals just agreed on one standard for AI agents
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI and four rivals just agreed on one standard for AI agents

**[The Next Web](https://daily.dev/sources/tnw)** · 3 min read · 0 upvotes · 0 comments

## Summary

OpenAI, Amazon, Microsoft, Cursor (Anysphere), and Vercel have jointly published Agent Plugins, an open standard that lets a single agent extension work across competing AI products. Initiated by Vercel and shaped by a five-member steering committee, the 1.0 spec defines a simple package format — a folder with a plugin.json file — bundling Model Context Protocol servers and reusable Agent Skills. At launch, ChatGPT, Codex, Cursor, GitHub Copilot, Kiro, and VS Code all support the format. The standard is deliberately narrow: it covers packaging and discovery but leaves marketplaces, permissions, sandboxing, and trust to individual clients. Reactions are mixed — some developers welcome a unified way to carry skills across tools, while others argue it is too thin and that useful parts will end up in client-specific extensions anyway.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://thenextweb.com/news/openai-agent-plugins-open-standard-skills-mcp>

## Questions this post answers

### What is the Agent Plugins open standard and which companies are behind it?

Agent Plugins is an open standard that lets a single agent extension work across competing AI products using one package format. It bundles Model Context Protocol servers and reusable Agent Skills into a folder with a plugin.json file at its root. The steering committee includes Amazon, Cursor (Anysphere), Microsoft, OpenAI, and Vercel — with Vercel having initiated the proposal. At launch, ChatGPT, Codex, Cursor, GitHub Copilot, Kiro, and VS Code all support it.

_Developers building or evaluating AI agent tooling track standards like this on daily.dev as they evolve._

### What does the Agent Plugins standard actually define and what does it leave out?

Agent Plugins defines only how a plugin is packaged and discovered — a folder with a plugin.json file bundling MCP servers and Agent Skills. It deliberately leaves out marketplaces, installation flows, permissions, sandboxing, and trust decisions, which remain each client's responsibility. Critics like SST framework author Dax Raad argue this makes it a thin standard whose useful parts will end up in client-specific extensions anyway.

_Teams deciding whether to build on Agent Plugins or wait for the ecosystem to mature follow these debates on daily.dev._

## Similar posts on daily.dev

- [Agent Plugins Explained: Skills and MCP in One Folder](https://daily.dev/posts/agent-plugins-explained-skills-and-mcp-in-one-folder-oszuhbwpc) · Medium · 4 upvotes · 0 comments
- [Anthropic defined the standards inside Agent Plugins. So why isn’t it helping govern the format?](https://daily.dev/posts/anthropic-defined-the-standards-inside-agent-plugins-so-why-isn-t-it-helping-govern-the-format--sjbkrjl67) · The New Stack · 0 upvotes · 0 comments
- [Vercel Introduces Skills.sh, an Open Ecosystem for Agent Commands](https://daily.dev/posts/vercel-introduces-skills-sh-an-open-ecosystem-for-agent-commands-cufa5edur) · InfoQ · 2 upvotes · 1 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#openai](https://daily.dev/tags/openai), [#mcp](https://daily.dev/tags/mcp)

[View this post on daily.dev](https://daily.dev/posts/openai-and-four-rivals-just-agreed-on-one-standard-for-ai-agents-ruwl1ozkg)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"OpenAI and four rivals just agreed on one standard for AI agents","url":"https://daily.dev/posts/openai-and-four-rivals-just-agreed-on-one-standard-for-ai-agents-ruwl1ozkg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/openai-and-four-rivals-just-agreed-on-one-standard-for-ai-agents-ruwl1ozkg"},"datePublished":"2026-08-08T00:18:41.939Z","dateModified":"2026-08-12T19:49:53.988Z","description":"OpenAI, Amazon, Microsoft, Cursor (Anysphere), and Vercel have jointly published Agent Plugins, an open standard that lets a single agent extension work across...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ff54804bbce32b0e2839c5be32b6d9ae?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ff54804bbce32b0e2839c5be32b6d9ae?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The Next Web","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The Next Web","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tnw","url":"https://daily.dev/sources/tnw"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/openai-and-four-rivals-just-agreed-on-one-standard-for-ai-agents-ruwl1ozkg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,openai,mcp","timeRequired":"PT3M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The Next Web","item":"https://daily.dev/sources/tnw"},{"@type":"ListItem","position":3,"name":"OpenAI and four rivals just agreed on one standard for AI agents"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/openai-and-four-rivals-just-agreed-on-one-standard-for-ai-agents-ruwl1ozkg#faq","mainEntity":[{"@type":"Question","name":"What is the Agent Plugins open standard and which companies are behind it?","acceptedAnswer":{"@type":"Answer","text":"Agent Plugins is an open standard that lets a single agent extension work across competing AI products using one package format. It bundles Model Context Protocol servers and reusable Agent Skills into a folder with a plugin.json file at its root. The steering committee includes Amazon, Cursor (Anysphere), Microsoft, OpenAI, and Vercel — with Vercel having initiated the proposal. At launch, ChatGPT, Codex, Cursor, GitHub Copilot, Kiro, and VS Code all support it. Developers building or evaluating AI agent tooling track standards like this on daily.dev as they evolve."}},{"@type":"Question","name":"What does the Agent Plugins standard actually define and what does it leave out?","acceptedAnswer":{"@type":"Answer","text":"Agent Plugins defines only how a plugin is packaged and discovered — a folder with a plugin.json file bundling MCP servers and Agent Skills. It deliberately leaves out marketplaces, installation flows, permissions, sandboxing, and trust decisions, which remain each client's responsibility. Critics like SST framework author Dax Raad argue this makes it a thin standard whose useful parts will end up in client-specific extensions anyway. Teams deciding whether to build on Agent Plugins or wait for the ecosystem to mature follow these debates on daily.dev."}}]}
```

