AG-UI: The Agent-User Interaction Protocol

AG-UI is an open, lightweight, event-based protocol that standardizes how AI agents connect to front-end applications.

➡️ See demos of AG-UI-enabled applications here

➡️ Learn more (AG-UI Specification)

AG-UI is an open, lightweight, event-based protocol for agent-human interaction, designed for simplicity & flexibility:

• During agent executions, agent backends emit events compatible with one of AG-UI’s 16 standard event types
• Agent backends can accept one of a few simple AG-UI compatible inputs as arguments

AG-UI includes a flexible middleware layer that ensures compatibility across diverse environments:

• Works with any event transport (SSE, WebSockets, webhooks, etc.)
• Allows for loose event format matching, enabling broad agent and app interoperability

It also ships with a reference HTTP implementation and default connector to help teams get started fast.

Learn more at docs.ag-ui.com

Why AG-UI?

AG-UI was developed based on real-world requirements and practical experience building in-app agent interactions.

It was shaped through:

• Working with users in the CopilotKit community to understand the needs of agent-based interactions in applications
• Collaborating closely with leading agent frameworks (LangGraph, Mastra, CrewAI, AG2, etc.)
• Extracting common infrastructure patterns that emerged across varied frameworks into a standardized, open protocol

This practical approach has helped ensure that AG-UI is both flexible and immediately applicable in real-world use cases.

➡️ Build AG-UI-Powered Applications

Play with this hello-world app here:
https://agui-demo.vercel.app/

Video:

https://github.com/user-attachments/assets/18c03330-1ebc-4863-b2b8-cc6c3a4c7bae

Select Your Language

• TypeScript
• Python

AG-UI Compatible Agent Frameworks

AG-UI works with several popular agent frameworks and frontend solutions:

Framework	Status	AG-UI Resources
LangGraph	✅ Supported	➡️ Live Demo / Getting Started Docs
Mastra	✅ Supported	➡️ Live Demo / Getting Started Docs
CrewAI	✅ Supported	➡️ Live Demo / Getting Started Docs
AG2	✅ Supported	➡️ Live Demo / Getting Started Docs
Agno	🛠️ In Progress	–
LlamaIndex	🛠️ In Progress	–
OpenAI Agent SDK	💡 Open to Contributions	–
Google ADK	💡 Open to Contributions	–
Vercel AI SDK	💡 Open to Contributions	–
AWS Bedrock Agents	💡 Open to Contributions	–
Cloudflare Agents	💡 Open to Contributions	–
Pydantic AI	💡 Open to Contributions	–
Strands Agents SDK	💡 Open to Contributions	–

Language SDK	Status	AG-UI Resources
.NET	🛠️ In Progress	➡️ PR
Nim	🛠️ In Progress	➡️ PR

Features

AG-UI-compatible agents securely and efficiently support:

• 💬 Agentic chat with real-time streaming
• 🔄 Bi-directional state sync (in and out of chat)
• 🧩 Generative UI and structured messages (with delta streaming)
• 🧠 Realtime context enrichment
• 🛠️ Frontend tool use (tool calls)
• 🧑‍💻 Human-in-the-loop and human-on-the-loop collaboration

And more. Learn more at ag-ui.com

AG-UI Showcase: The AG-UI Dojo (Building-Blocks Viewer)

The ag-ui dojo showcases many of the building blocks that ag-ui supports.

The building blocks are designed to be simple and focused – between 50-200 lines of code.

https://github.com/user-attachments/assets/a67d3d54-36b2-4c7a-ac69-a0ca01365d5b

Client Libraries

AG-UI provides ready-to-use client libraries for building connected experiences:

• React client via CopilotKit
• Messaging clients (WhatsApp, WeChat, RCS) — WIP in collaboration with AWS SNS

➡️ Contribute to AG-UI

Learn how to contribute to AG-UI: AG-UI Contribution Guide

Book time with Markus Ecker, the creator of AG-UI: https://calendly.com/markus-copilotkit/ag-ui

Join the Discord: https://discord.gg/Jd3FzfdJa8

Community

Upcoming Events

• AG-UI: Workshop
  📅 Friday, June 5, 9:00 AM PT
  🔗 Register now

Contributing

We 💜 contributions! Whether you’re fixing bugs, improving documentation, or building demos — your contributions make AG-UI better.