base on null # Generative UI SDK for Flutter (genui) A Flutter library to enable developers to easily add interactive generative UI to their applications. See the [Getting started with GenUI](https://www.youtube.com/watch?v=nWr6eZKM6no) video for an overview of the package. [<img src="docs/assets/genui_intro_video_still.png" alt="GenUI Intro video still" height="500">](https://www.youtube.com/watch?v=nWr6eZKM6no) ## Status: highly experimental This is a highly experimental package, which means the API will change (sometimes drastically). [Feedback is very welcome](https://github.com/flutter/genui/issues/new/choose). ## 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 ### Interactive [travel app example](examples/travel_app/) <img src="docs/assets/travel_app_genui_example.gif" alt="GenUI Travel App Demo" height="500"> _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. <img src="docs/assets/travel_app_genui_example.png" alt="GenUI Features Breakdown" height="600"> ## 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 uses a `ContentGenerator` to communicate with a generative AI model, allowing `genui` to be backend agnostic. You can choose the implementation that best fits your needs, whether it's `FirebaseAiContentGenerator` for production apps, `GoogleGenerativeAiContentGenerator` for rapid prototyping, or `A2uiContentGenerator` for custom agent servers. See the package table below for more details on each. ## Packages | Package | Description | Version | | :--- | :--- | :--- | | [genui](packages/genui/) | The core framework to employ Generative UI. | [](https://pub.dev/packages/genui) | | [genui_firebase_ai](packages/genui_firebase_ai/) | Provides **`FirebaseAiContentGenerator`** to connect to Gemini via Firebase AI Logic. This is the recommended approach for production apps based on client-side agents. | [](https://pub.dev/packages/genui_firebase_ai) | | [genui_google_generative_ai](packages/genui_google_generative_ai/) | Provides **`GoogleGenerativeAiContentGenerator`** for connecting to the Google Generative AI API with only an API key. Ideal for getting started quickly. | [](https://pub.dev/packages/genui_google_generative_ai) | | [genui_a2ui](packages/genui_a2ui/) | Provides **`A2uiContentGenerator`** for connecting to any server that implements the [A2UI protocol](https://a2ui.org). Use this for integrating with custom agent backends. | [](https://pub.dev/packages/genui_a2ui) | | [genui_dartantic](packages/genui_dartantic/) | Integration package for genui and Dartantic AI. | [](https://pub.dev/packages/genui_dartantic) | | [json_schema_builder](packages/json_schema_builder/) | A fully featured Dart JSON Schema package with validation, used by the core framework to define widget data structures. | [](https://pub.dev/packages/json_schema_builder) | ### Dependencies This diagram shows how packages depend on each other and how examples use them. ```mermaid graph TD examples/simple_chat --> genui_google_generative_ai examples/simple_chat --> genui_firebase_ai examples/travel_app --> genui_google_generative_ai examples/travel_app --> genui_firebase_ai examples/verdure --> genui_a2ui examples/custom_backend --> genui genui --> json_schema_builder genui_a2ui --> genui genui_dartantic --> genui genui_firebase_ai --> genui genui_google_generative_ai --> genui ``` ## Getting started See the [genui getting started guide](packages/genui/README.md#getting-started-with-genui). ## Constraints This repo requires Flutter version >=3.35.7. ## Some things we're thinking about - **Genkit Integration:** Integration with Genkit. - **ADK Plugin:** turnkey integration with ADK. - **Expanded LLM Framework Support:** Official support for additional LLM frameworks. - **Streaming UI:** Support for progressively rendering UI components as they stream from the LLM. - **Full-Screen Composition:** Enable LLM-driven composition and navigation of entire app screens. - **A2A Agent Support:** Support for A2A agent interactions. - **Dart Bytecode:** Future support for Dart Bytecode for even greater dynamism and flexibility. ## Contribute See [CONTRIBUTING.md](CONTRIBUTING.md) ", Assign "at most 3 tags" to the expected json: {"id":"15247","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"