OpenAI Launches Agent Plugins — A New Standard for Agent Clients
OpenAI Launches Agent Plugins — A New Standard for Agent Clients
OpenAI, along with AWS and other companies, launches Agent Plugins — a new open standard for agent clients. This will simplify the setup process for tools across different platforms.
OpenAI Launches Agent Plugins
OpenAI, together with AWS, Cursor, GitHub, VS Code, Vercel, and others, is launching Agent Plugins — an open standard for packaging skills and configurations of MCP servers into a single format.
One such package can be used across various compatible agent clients. Initially, it supports Codex, ChatGPT, Cursor, GitHub Copilot, VS Code, and Kiro.
The most useful aspect here is that instructions can finally be transferred along with the necessary tools. No longer will developers need to reassemble and configure the same setup for each client.
Currently, the first version standardizes only the package format. Authentication, permissions, installation, and interface remain on the client side.
Claude Code is not included in the initial list yet.
Why it matters
AnalysisThis new standard will streamline the integration and setup of tools for developers, saving time and effort. It's an important step in the development of autonomous agents and their interactions.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Four Resume Tips from OpenAI’s Head of Applied AI Development
Wulfie Bain, OpenAI’s head of applied AI development, shared four resume rules: keep it short, remove irrelevant details, highlight outcomes, and lead with the strongest achievements.
AI Radar: GPT-6.1 Terra, Gemini 4 Carbon, Mistral Large 4 and OpenAI/Anthropic pricing changes
A roundup of recent AI news: new LLM releases, OpenAI and Anthropic subscription changes, world models, video generation, and research updates.
Part I. AI Agent Architecture: The Foundations
The eleven foundational building blocks of modern autonomous agents: model taxonomy, the agentic runtime loop, advanced prompting, distillation, skills architecture, memory systems, function calling, and FinOps.
Part II. AI Agent Architecture: From Model to Memory and Tools
A deep engineering dive: tokenization, KV-cache, sampling determinism, the training stack, quantization, context engineering, the safety stack, production RAG, ReAct, and multi-agent swarm systems.