The Wayback Machine - https://web.archive.org/web/20260512144842/https://docs.ag-ui.com/introduction
Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.ag-ui.com/llms.txt

Use this file to discover all available pages before exploring further.

ā€‹
The Agentā€“User Interaction (AG-UI) Protocol

AG-UI is an open, lightweight, event-based protocol that standardizes how AI agents connect to user-facing applications. AG-UI is designed to be the general-purpose, bi-directional connection between a user-facing application and any agentic backend. Built for simplicity and flexibility, it standardizes how agent state, UI intents, and user interactions flow between your model/agent runtime and user-facing frontend applicationsā€”to allow application developers to ship reliable, debuggable, userā€‘friendly agentic features fast while focusing on application needs and avoiding complex ad-hoc wiring.
AG-UI Overview

ā€‹
Agentic Protocols

Confused about ā€œA2UIā€ and ā€œAG-UIā€? Thatā€™s understandable! Despite the naming similarities, they are quite different and work well together. A2UI is a generative UI specification - allowing agents to deliver UI widgets, where AG-UI is the Agentā†”User Interaction protocol - which connects an agentic frontend to any agentic backend. Learn more
AG-UI is one of three prominent open agentic protocols.
LayerProtocol / ExamplePurpose
Agent ā†” User InteractionAG-UI
(Agentā€“User Interaction Protocol)		The open, event-based standard that connects agents to user-facing applications ā€” enabling real-time, multimodal, interactive experiences.
Agent ā†” Tools & DataMCP
(Model Context Protocol)		Open standard (originated by Anthropic) that lets agents securely connect to external systems ā€” tools, workflows, and data sources.
Agent ā†” AgentA2A
(Agent to Agent)		Open standard (originated by Google) which defines how agents coordinate and share work across distributed agentic systems.

ā€‹
Building blocks (today & upcoming)

Streaming chat
Live token and event streaming for responsive multi turn sessions, with cancel and resume.
Multimodality
Typed attachments and real time media (files, images, audio, transcripts); supports voice, previews, annotations, provenance.
Generative UI, static
Render model output as stable, typed components under app control.
Generative UI, declarative
Small declarative language for constrained yet open-ended agent UIs; agents propose trees and constraints, the app validates and mounts.
Shared state
(Read-only & read-write). Typed store shared between agent and app, with streamed event-sourced diffs and conflict resolution for snappy collaboration.
Thinking steps
Visualize intermediate reasoning from traces and tool events; no raw chain of thought.
Frontend tool calls
Typed handoffs from agent to frontend-executed actions, and back.
Backend tool rendering
Visualize backend tool outputs in app and chat, emit side effects as first-class events.
Interrupts (human in the loop)
Pause, approve, edit, retry, or escalate mid flow without losing state.
Sub-agents and composition
Nested delegation with scoped state, tracing, and cancellation.
Agent steering
Dynamically redirect agent execution with real-time user input to guide behavior and outcomes.
Tool output streaming
Stream tool results and logs so UIs can render long-running effects in real time.
Custom events
Open-ended data exchange for needs not covered by the protocol.

ā€‹
Why Agentic Apps need AG-UI

Agentic applications break the simple request/response model that dominated frontend-backend development in the pre-agentic era: a client makes a request, the server returns data, the client renders it, and the interaction ends.

ā€‹
The requirements of userā€‘facing agents

While agents are just software, they exhibit characteristics that make them challenging to serve behind traditional REST/GraphQL APIs:
  • Agents are longā€‘running and stream intermediate workā€”often across multiā€‘turn sessions.
  • Agents are nondeterministic and can control application UI nondeterministically.
  • Agents simultanously mix structured + unstructured IO (e.g. text & voice, alongside tool calls and state updates).
  • Agents need user-interactive composition: e.g. they may call subā€‘agents, often recursively.
  • And moreā€¦
AG-UI is an event-based protocol that enables dynamic communication between agentic frontends and backends. It builds on top of the foundational protocols of the web (HTTP, WebSockets) as an abstraction layer designed for the agentic ageā€”bridging the gap between traditional client-server architectures and the dynamic, stateful nature of AI agents.

ā€‹
AG-UI in Action

You can see demo apps of the AG-UI features with the framework of your choice, with preview, code, and walkthrough docs in the AG-UI Dojo

ā€‹
Supported Integrations

AG-UI was born from CopilotKitā€™s initial partnership with LangGraph and CrewAI - and brings the incredibly popular agent-user-interactivity infrastructure to the wider agentic ecosystem. 1st party = the platforms that have AGā€‘UI built in and provide documentation for guidance.

ā€‹
Direct to LLM

FrameworkStatusAG-UI Resources
Direct to LLMSupportedDocs

ā€‹
Agent Framework - Partnerships

FrameworkStatusAG-UI Resources
LangGraphSupportedDocs, Demos
CrewAISupportedDocs, Demos

ā€‹
Agent Framework - 1st Party

FrameworkStatusAG-UI Resources
Microsoft Agent FrameworkSupportedDocs, Demos
Google ADKSupportedDocs, Demos
AWS Strands AgentsSupportedDocs, Demos
AWS Bedrock AgentCoreSupportedDocs
MastraSupportedDocs, Demos
Pydantic AISupportedDocs, Demos
AgnoSupportedDocs, Demos
LlamaIndexSupportedDocs, Demos
AG2SupportedDocs Demos
AWS Bedrock AgentsIn Progressā€“

ā€‹
Agent Framework - Community

FrameworkStatusAG-UI Resources
OpenAI Agent SDKIn Progressā€“
Cloudflare AgentsIn Progressā€“

ā€‹
Agent Interaction Protocols

ProtocolStatusAG-UI ResourcesIntegrations
A2A MiddlewareSupportedDocsPartnership

ā€‹
Infrastructure / Deployment

PlatformStatusAG-UI ResourcesIntegrations
Amazon Bedrock AgentCoreSupportedDocs1st Party

ā€‹
Specification (standard)

FrameworkStatusAG-UI Resources
Oracle Agent SpecSupportedDocs, Demos

ā€‹
SDKs

SDKStatusAG-UI ResourcesIntegrations
KotlinSupportedGetting StartedCommunity
GolangSupportedGetting StartedCommunity
DartSupportedGetting StartedCommunity
JavaSupportedGetting StartedCommunity
RustSupportedGetting StartedCommunity
.NETIn ProgressPRCommunity
NimIn ProgressPRCommunity
FlowiseIn ProgressGitHub SourceCommunity
LangflowIn ProgressGitHub SourceCommunity

ā€‹
Clients

ClientStatusAG-UI ResourcesIntegrations
CopilotKitSupportedGetting Started1st Party
Terminal + AgentSupportedGetting StartedCommunity
React NativeHelp WantedGitHub SourceCommunity

ā€‹
Quick Start

Choose the path that fits your needs:

Build agentic applications

Build agentic applications powered by AG-UI compatible agents.

Build new AG-UI integrations

Build integrations for new agent frameworks, custom in-house solutions, or use AG-UI without any agent framework.

Build AG-UI compatible clients

Build new clients for AG-UI-compatible agents (web, mobile, slack, messaging, etc.)

ā€‹
Explore AG-UI

Dive deeper into AG-UIā€™s core concepts and capabilities:

Core architecture

Understand how AG-UI connects agents, protocols, and front-ends

Events

Learn about AG-UIā€™s event-driven protocol

ā€‹
Resources

Explore guides, tools, and integrations to help you build, optimize, and extend your AG-UI implementation. These resources cover everything from practical development workflows to debugging techniques.

Developing with Cursor

Use Cursor to build AG-UI implementations faster

Troubleshooting AG-UI

Fix common issues when working with AG-UI servers and clients

ā€‹
Contributing

Want to contribute? Check out our Contributing Guide to learn how you can help improve AG-UI.

ā€‹
Support and Feedback

Hereā€™s how to get help or provide feedback:
  • For bug reports and feature requests related to the AG-UI specification, SDKs, or documentation (open source), please create a GitHub issue
  • For discussions or Q&A about AG-UI, please join the Discord community