Technology Radar
AG-UI is an open protocol and library designed to standardize communication between rich user interfaces and back-end AI agents. Historically, building agentic UIs required bespoke plumbing for bidirectional, stateful collaboration. AG-UI addresses this by providing a consistent, event-driven architecture — supporting transports such as server-sent events (SSE) and WebSockets — for streaming reasoning steps, synchronizing state and rendering dynamic UI components.
However, the architectural landscape for agent interfaces is shifting rapidly. AG-UI intentionally sits outside MCP, functioning as an interface layer between the frontend and the agent backend. We’re now seeing a different approach emerge, where newer MCP-based applications package HTML and UI widgets directly within MCP servers or skills.
Because UI components can now be embedded and served alongside the tools themselves — a pattern related to emerging adjacent standards such as MCP-UI — the need for a separate UI protocol layer such as AG-UI is being questioned. While AG-UI remains a solid choice for decoupling front-end UX from back-end orchestration, teams should assess its role in light of the growing trend toward consolidating tool logic and UI within the MCP ecosystem.
AG-UI es un protocolo abierto y una biblioteca diseñados para estandarizar la comunicación entre interfaces de usuario avanzados y agentes. Enfocado a agentes que interactúan directamente con usuarios finales, utiliza un middleware e integraciones de cliente para generalizar en cualquier frontend y backend. El protocolo define una forma coherente para que los agentes del backend se comuniquen con las aplicaciones del frontend, permitiendo una colaboración en tiempo real y con estado entre la IA y los usuarios. Es compatible con múltiples protocolos de transporte, incluidos SSE y WebSockets, y proporciona tipos de eventos estandarizados para representar diferentes estados de ejecución del agente. Ofrece soporte integrado para frameworks de agentes populares como LangGraph y Pydantic AI, con integraciones de la comunidad para otros.
