AG-UI is a lightweight, event-based protocol that standardizes how AI agents connect to front-end applications. Built for simplicity and flexibility, it enables seamless integration between your AI agents and user interfaces.
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.
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
AG-UI was developed based on real-world requirements and practical experience building in-app agent interactions.
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
- 💬 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
AG-UI integrates with many popular agent frameworks
| Framework | Status | AG-UI Resources |
|---|---|---|
| No-framework | ✅ Supported | ➡️ Docs coming soon |
| LangGraph | ✅ Supported | ➡️ Demo |
| Mastra | ✅ Supported | ➡️ Demo |
| CrewAI | ✅ Supported | ➡️ Demo |
| AG2 | ✅ Supported | ➡️ Demo |
| Agno | 🛠️ In Progress | – |
| LlamaIndex | 🛠️ In Progress | – |
| Pydantic AI | 🛠️ In Progress | – |
| Vercel AI SDK | 🛠️ In Progress | – |
| OpenAI Agent SDK | 💡 Open to Contributions | – |
| Google ADK | 💡 Open to Contributions | – |
| AWS Bedrock Agents | 💡 Open to Contributions | – |
| Cloudflare Agents | 💡 Open to Contributions | – |
| Strands Agents SDK | 💡 Open to Contributions | – |
| Language SDK | Status | AG-UI Resources |
|---|---|---|
| .NET | 🛠️ In Progress | ➡️ PR |
| Nim | 🛠️ In Progress | ➡️ PR |
| Rust | 🛠️ In Progress |
View all supported frameworks →
Play with this hello-world app here: https://agui-demo.vercel.app/
agui-hello-world-2.mp4
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.
Choose your path:
Create a new AG-UI application in seconds:
npx create-ag-ui-app my-agent-appView Documentation · Join Discord
- Build new integrations (Quickstart)
- Book a call to discuss an AG-UI integration with a new framework
- Join the Discord Community
Check out the Contributing guide
- AG-UI: Build an agent canvas with AG-UI
📅 Friday, June 20, 9:00 AM PT
AG-UI is open source and available under the MIT License.