AG-UI
The third agent protocol — not agent to tool, nor agent to agent, but agent to user interface
What is AG-UI?
A request-and-response API cannot describe an agent that runs for minutes, streams partial work, changes its mind and occasionally needs a person. AG-UI defines that exchange as a stream of events over HTTP and WebSockets: tokens, tool calls and their results, shared state, attachments, and interrupts where the run stops to ask. Its usefulness scales with what already implements it — a first-party list that includes several frameworks in this catalogue — and drops sharply if neither your backend nor your frontend does.
What can you do with AG-UI?
- Show the work, not a spinner — Token-level updates, tool calls and tool results arrive as separate events, so an interface can display what the agent is doing while it is still doing it instead of waiting for a final payload.
- Keep one state on both sides — State is shared between the agent and the application as part of the protocol, so the frontend reads it directly rather than reconstructing the agent's view by parsing the transcript.
- Stop and ask the person — Human-in-the-loop interrupts are part of the event vocabulary, which means approval steps are a protocol feature every implementation handles the same way rather than something each application invents.
- Send more than text — Files, images, audio and transcripts are carried as multimodal attachments, and the agent can emit declarative UI components for the application to render.
- Connect a backend that already speaks it — First-party implementations include CopilotKit, Microsoft Agent Framework, Google ADK, AWS Strands, Mastra, Pydantic AI, LlamaIndex and AG2, with partnerships covering LangGraph and CrewAI.
Before you choose AG-UI
- The payoff is proportional to what already implements it: with a hand-built frontend and a backend outside the supported list, this is a specification to implement at both ends, not a component to install.
Star history
21 Aug to 28 Aug · +131
Frequently asked questions
Is AG-UI free for commercial use?
AG-UI is released under the MIT licence — OSI-approved open source, which permits commercial use.
How can AG-UI be deployed?
AG-UI is available as Self-hosted / Runs locally.
Documentation
Reproduced from the ag-ui-protocol/ag-ui README, published under MIT. Read the original ↗
AG-UI: The Agent-User Interaction Protocol
AG-UI is an open, lightweight, event-based protocol that standardizes how AI agents connect to user-facing applications. Built for simplicity and flexibility, it enables seamless integration between AI agents, real time user context, and user interfaces.
Join our Discord → Read the Docs → Go to the AG-UI Dojo → Follow us →
🚀 Getting Started
Create a new AG-UI application in seconds:
npx create-ag-ui-app my-agent-app- The AG-UI Dojo
- Build AG-UI-powered applications(Quickstart)
- Build new AG-UI framework integrations (Quickstart)
- Book a call to discuss an AG-UI integration with a new framework
- Join the Discord Community
What is AG-UI?
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.
Why AG-UI?
AG-UI was developed based on real-world requirements and practical experience building in-app agent interactions.
Where does AGUI fit in the agentic protocol stack?
AG-UI is complementary to the other 2 top agentic protocols
- MCP gives agents tools
- A2A allows agents to communicate with other agents
- AG-UI brings agents into user-facing applications
🚀 Features
- 💬 Real-time agentic chat with streaming
- 🔄 Bi-directional state synchronization
- 🧩 Generative UI and structured messages
- 🧠 Real-time context enrichment
- 🛠️ Frontend tool integration
- 🧑💻 Human-in-the-loop collaboration
🛠 Supported Integrations
AG-UI was born from CopilotKit’s initial partnership with LangChain and CrewAI - and brings the incredibly popular agent-user-interactivity infrastructure to the wider agentic ecosystem.
1st party = the platforms that have AG‑UI built in and provide documentation for guidance.
Frameworks
| Framework | Status | AG-UI Resources |
|---|---|---|
| Built-in Agent | ✅ Supported | ➡️ Docs |
🤝 Partnerships
| Framework | Status | AG-UI Resources |
|---|---|---|
| LangChain | ✅ Supported | ➡️ Docs 🎮 Demos |
| CrewAI | ✅ Supported | ➡️ Docs 🎮 Demos |
🧩 1st Party
| Framework | Status | AG-UI Resources |
|---|---|---|
| Microsoft Agent Framework | ✅ Supported | ➡️ Docs 🎮 Demos |
| Google ADK | ✅ Supported | ➡️ Docs 🎮 Demos |
| AWS Strands Agents | ✅ Supported | ➡️ Docs 🎮 Demos |
| Mastra | ✅ Supported | ➡️ Docs 🎮 Demos |
| Pydantic AI | ✅ Supported | ➡️ Docs 🎮 Demos |
| Agno | ✅ Supported | ➡️ Docs 🎮 Demos |
| LlamaIndex | ✅ Supported | ➡️ Docs 🎮 Demos |
| AG2 | ✅ Supported | ➡️ Docs 🎮 Demos |
| AWS Bedrock Agents | 🛠️ In Progress | – |
🌐 Community
| Framework | Status | AG-UI Resources |
|---|---|---|
| Claude Agent SDK | ✅ Supported | 🎮 Demos |
| Claude Managed Agents SDK | ✅ Supported | 🎮 Demos |
| Langroid | ✅ Supported | 🎮 Demos |
| OpenAI Agent SDK | 🛠️ In Progress | – |
| Cloudflare Agents | 🛠️ In Progress | – |
Agent Interaction Protocols
| Protocols | Status | AG-UI Resources | Integrations |
|---|---|---|---|
| A2A | ✅ Supported | ➡️ Docs | Partnership |
Infrastructure / Deployment
| Platform | Status | AG-UI Resources | Integrations |
|---|---|---|---|
| Amazon Bedrock AgentCore | ✅ Supported | ➡️ Docs | 1st Party |
Specification (standard)
| Framework | Status | AG-UI Resources |
|---|---|---|
| Oracle Agent Spec | ✅ Supported | ➡️ Docs 🎮 Demos |
Generative UI
| Framework | Status | AG-UI Resources |
|---|---|---|
| MCP Apps | ✅ Supported | ➡️ Docs 🎮 Demos |
SDKs
| SDK | Status | AG-UI Resources | Integrations |
|---|---|---|---|
| Kotlin | ✅ Supported | ➡️ Getting Started | Community |
| Golang | ✅ Supported | ➡️ Getting Started | Community |
| Dart | ✅ Supported | ➡️ Getting Started | Community |
| Java | ✅ Supported | ➡️ Getting Started | Community |
| Rust | ✅ Supported | ➡️ Getting Started | Community |
| Ruby | ✅ Supported | ➡️ Getting Started | Community |
| C++ | ✅ Supported | ➡️ GitHub Source | Community |
| .NET | ✅ Supported | ➡️ Getting Started | Community |
| Nim | 🛠️ In Progress | ➡️ PR | Community |
| Flowise | 🛠️ In Progress | ➡️ GitHub Source | Community |
| Langflow | 🛠️ In Progress | ➡️ GitHub Source | Community |
Clients
| Client | Status | AG-UI Resources | Integrations |
|---|---|---|---|
| CopilotKit | ✅ Supported | ➡️ Getting Started | 1st Party |
| Terminal + Agent | ✅ Supported | ➡️ Getting Started | Community |
| Chat platforms (Slack, Microsoft Teams) | ✅ Supported | ➡️ Channels SDK 🎮 OpenTag example | 1st Party |
| React Native | ✅ Supported | ➡️ Example | 1st Party |
View all supported integrations →
Examples
Hello World App
Video:
https://github.com/user-attachments/assets/18c03330-1ebc-4863-b2b8-cc6c3a4c7bae
The AG-UI Dojo (Building-Blocks Viewer)
The AG-UI Dojo demonstrates AG-UI’s core building blocks through simple, focused examples—each just 50-200 lines of code.
View the source code for the Dojo and all framework integrations here.
https://github.com/user-attachments/assets/c298eea8-3f39-4a94-b968-7712429b0c49
🙋🏽♂️ Contributing to AG-UI
Check out the Contributing guide
- Biweekly AG-UI Working Group 📅 Follow the CopilotKit Luma Events Calendar
Roadmap
Check out the AG-UI Roadmap to see what’s being built and where you can jump in.
📄 License
AG-UI is open source software licensed as MIT.
Other options in Protocols & Interop
MCP Reference ServersProtocolsThe clearest way to understand the Model Context Protocol is to read servers that implement it correctly, and this is that collection. Useful both as working connectors and as the template to copy when writing your own.
Context7ProtocolsAsk for a library by name and Context7 resolves it to an identifier like /vercel/next.js, then answers queries with version-specific snippets from a continuously re-indexed documentation corpus — so the model writes against the API that exists today rather than the one in its training data. Setup is one command or a URL pasted into any MCP client, and anyone can submit a public repository to the index. Know what you are adopting: the open-source part is a thin client, while the crawler, parser and index are Upstash's private hosted service — the free tier stops at 1,000 calls a month, and when the hosted endpoint went down for a stretch in August 2026, the tool had nothing to answer from.
chrome-devtools-mcpProtocolsIt hands an agent a live Chrome plus the instruments of DevTools: it records a performance trace and reads out Core Web Vitals with named insights, lists network requests and source-mapped console errors, runs Lighthouse audits, and still clicks and fills forms from a text snapshot of the page the way browser MCPs do. It can attach to the Chrome you already have open, profile and all — which is also where care is needed. The trade against Playwright MCP is scope: this is Chrome-only, and what that buys is analysis no cross-browser server offers.