genui는 AI를 활용하여 생성형 사용자 인터페이스(GenUI)의 생성과 표시를 가능하게 하는 Flutter 패키지입니다. 대규모 언어 모델(LLMs)과 통합되어 자연어 프롬프트에 기반해 UI 컴포넌트를 동적으로 생성함으로써 앱 개발을 간소화합니다. 빠른 프로토타이핑과 상호작용 디자인을 위해 설계되었으며, 개발자가 일반 텍스트로 원하는 레이아웃이나 기능을 설명할 수 있도록 하여 이를 기능적인 Flutter 위젯으로 렌더링합니다. Android, iOS, Web, macOS 등 여러 플랫폼을 지원하여 크로스플랫폼 프로젝트에 유연하게 적용할 수 있습니다.
사용 사례
빠른 UI 프로토타이핑
AI 기반 디자인 생성
인터랙티브 앱 개발
자연어에서 UI로의 변환
크로스 플랫폼 UI 생성
주요 기능
AI 기반 UI 생성
UI 설계를 위한 자연어 입력
다중 플랫폼 지원
실시간 UI 렌더링
LLM과의 통합
적합한 대상
앱 디자인에서 AI를 사용하는 개발자
프로토타이핑 팀
크로스 플랫폼 앱 제작자
자동화를 찾는 디자이너
Flutter 초보자가 GenAI 탐구 중
고려 사항
LLM 호출을 위해 인터넷 연결이 필요합니다
일관되지 않은 출력을 생성할 수 있습니다
프롬프트 품질에 따라 다릅니다
초기 버전에서의 맞춤 설정 제한
UI 생성 시 잠재적인 지연
원본 README
연결된 소스 저장소의 README 원문 스냅샷입니다. 최신 내용은 저장소에서 확인하세요.
Generative UI SDK for Flutter (genui)
A Flutter library to enable developers to easily add interactive
generative UI to their applications.
This is a highly experimental package, which means the API will change (sometimes drastically).
Feedback is very welcome.
Summary
Our goal for the GenUI SDK for Flutter is to help you replace static "walls of text" from your LLM with
dynamic, interactive, graphical UI.
It uses a JSON-based format to compose UIs from your existing widget catalog, turning
conversations or agent interactions into rich, intuitive experiences. State changes in the UI update
a client-side data model, which is fed back to the agent, creating a
powerful, high-bandwidth interaction loop. The GenUI SDK for Flutter aims to be easy to integrate
into your Flutter application to significantly improve the usability and satisfaction of your
chatbots and next-generation agent-based user experiences.
High-level goals
Increase Interaction Bandwidth for Users: allow users to interact with data and controls directly,
making task completion faster and more intuitive. Move beyond a "wall of text".
Simple and easy to use by developers: seamlessly integrate with your existing Flutter workflow,
design systems, and widget catalogs.
Drive agent-human UX forward: innovate ways to dramatically improve how users interact with their
LLMs and Agents. Radically simplify the process of building UI-based agent interactions, by
eliminating custom middleware between the agent and the UI layer.
Features
Multiple agent and LLM provider support
A2UI support
Standard UI catalog
Custom widgets
Data binding
Chat UX
Canvas UX
Use cases
Incorporate graphical UI into chatbots: instead of describing a list of products in text,
the LLM can render an interactive carousel of product widgets. Instead of asking for a user to
type out answers to questions, the LLM can render sliders, checkboxes, and more.
Create dynamically composed UIs: an agent can generate a complete form with sliders, date pickers,
and text fields on the fly based on a user's request to "book a flight."
Look & feel
The GIF above shows how GenUI enables dynamic, interactive UI generation,instead of text descriptions or code from a traditional AI coding agent.
Core difference
This UI is not generated in the form of code; rather, it's generated at runtime
based on a widget catalog from the developers' project.
Implementation goals
Integrate with your LLM: Work with your chosen LLM and backend to incorporate graphical
UI responses alongside traditional text.
Leverage Your Widget Catalog: Render UI using your existing, beautifully crafted widgets
for brand and design consistency.
Interactive State Feedback: Widget state changes are sent back to the LLM, enabling a
true interactive loop where the UI influences the agent's next steps.
Framework Agnostic: Be integrated into your agent library or LLM framework of choice.
JSON Based: Use a simple, open standard for UI definition—no proprietary formats.
Cross-Platform Flutter: Work anywhere Flutter works (mobile, iOS, Android, Web, and more).
Widget Composition: Support nested layouts and composition of widgets for complex UIs.
Basic Layout: LLM-driven basic layout generation.
Any Model: Integrate with any LLM that can generate structured JSON output.
Connecting to an AI agent
The genui framework is designed to be backend agnostic. You can use any AI SDK (such as firebase_ai or dartantic_ai) to generate content. The framework provides adapters (like A2uiTransportAdapter) to ingest the AI response and render it.
For custom agent servers that implement the A2UI protocol, you can use the genui_a2a package.
See the package table below for more details on each.
The Flutter Gen UI SDK uses the A2UI protocol to represent UI content internally. The genui_a2a package allows it to act as a renderer for UIs generated by an A2UI backend agent, similar to the other A2UI renderers which are maintained within the A2UI repository.
The Flutter Gen UI SDK currently supports A2UI v0.9.
This repo contains skill files for developers building with agentic coding tools. They can be copied directly into an agent's preferred location or installed using the skills package: