--- title: "What is AG-UI? The Agent-User Interaction protocol" description: "AG-UI (the Agent-User Interaction Protocol) is CopilotKit's open, lightweight, event-based protocol that standardises how AI agents connect to user-facing applications — a run request carries the conversation, shared state, and frontend-offered tools, and the agent streams typed events back over SSE or WebSockets." last_updated: 2026-07-17 canonical_url: https://agent-ready.dev/what-is-ag-ui --- # What is AG-UI? > CopilotKit's open event-based protocol connecting agent backends to user-facing apps. ## At a glance - **Definition:** "an open, lightweight, event-based protocol that standardizes how AI agents connect to user-facing applications" — CopilotKit's general-purpose, bi-directional connection between a user-facing application and any agentic backend. - **Stack:** the agent↔user layer of a three-layer protocol stack, alongside MCP (agent↔tools, from Anthropic) and [A2A](https://agent-ready.dev/mcp-vs-a2a-vs-agents-json) (agent↔agent, from Google). Complementary, not competitors. - **Transports:** HTTP with Server-Sent Events (SSE) or WebSockets — an abstraction layer over standard web protocols, so no exotic infrastructure is required. - **Event categories:** around 30 standard events across seven categories — Lifecycle, Text messages, Tool calls, State, Activity, Reasoning, and Special — every event carrying `type`, `timestamp`, and `rawEvent` fields. Wire `type` strings are SCREAMING_SNAKE_CASE (e.g. `RUN_STARTED`). ## AG-UI vs A2UI A2UI (Google) is a declarative generative-UI **payload** format: the agent returns a JSON component tree the client renders. AG-UI (CopilotKit) is the event-based **wire protocol** between an agent backend and a frontend. They sit at different layers — an A2UI payload can be delivered over AG-UI (or A2A). Payload versus pipe. See [What is A2UI?](https://agent-ready.dev/what-is-a2ui). ## Frequently asked questions ### What is AG-UI? AG-UI (the Agent-User Interaction Protocol) is CopilotKit's open, lightweight, event-based protocol that standardises how AI agents connect to user-facing applications. The frontend sends a run request carrying the conversation, shared state, and the tools it offers, and the agent streams back a sequence of typed events over SSE or WebSockets. Created by CopilotKit and launched in May 2025, it is MIT-licensed and lives at ag-ui-protocol/ag-ui on GitHub. ### What is the difference between AG-UI and A2UI? They sit at different layers. A2UI is Google's declarative payload format — the agent returns a JSON component tree the client renders. AG-UI is CopilotKit's event-based wire protocol between an agent backend and a frontend, so an A2UI payload can be delivered over AG-UI (or over A2A). Payload versus pipe. ### How does AG-UI relate to MCP and A2A? They are complementary layers of one stack, not competitors. MCP (from Anthropic) standardises how an agent reaches tools and data; A2A (from Google) standardises how agents talk to each other; AG-UI (from CopilotKit) standardises how an agent run reaches the person using the app. The same agent typically speaks both MCP and AG-UI. ### Which frameworks support AG-UI? AG-UI ships SDKs in TypeScript and Python — CopilotKit is the primary client implementation — with community SDKs in Kotlin, Go, Dart, Java, and Rust, and .NET and Nim in progress. Partnership integrations cover LangGraph and CrewAI; first-party integrations include Microsoft Agent Framework, Google ADK, AWS Strands Agents, AWS Bedrock AgentCore, Mastra, Pydantic AI, Agno, LlamaIndex, and AG2. The OpenAI Agent SDK, Cloudflare Agents, and AWS Bedrock Agents are in progress. ### Do I need special infrastructure to run AG-UI? No. AG-UI is an abstraction layer over standard web protocols — HTTP with Server-Sent Events (SSE) or WebSockets — so it needs no exotic infrastructure. An agent backend exposes an endpoint, the frontend sends a run request, and the backend streams typed events back. You deploy it on ordinary web infrastructure you already run. ### Does Agent Ready check for AG-UI? Not yet. AG-UI defines no publisher-side static discovery artifact — no /.well-known/ path, no manifest, no schema a crawler can fetch — so there is nothing for a static scanner to probe; it is a runtime conversation between a deployed agent backend and a running frontend. Agent Ready's protocol checks are discover-then-validate over static artifacts, and if AG-UI ever ships a static discovery surface a check would follow. Sites that publish nothing are never penalised. --- Read the full guide on the web: Score your site for agents: ## Sitemap See the full [sitemap](https://agent-ready.dev/sitemap.md) for all pages on agent-ready.dev.