Generative UI Starter Project

A chat-driven kanban board where you and the agent work the same task list. Built with CopilotKit, AG-UI, and LangGraph on top of Next.js. Also doubles as a starter for declarative gen UI via A2UI (flight-search example included).

Gen UI concept - shared agent state. The board (To Do / Done columns) lives in the agent and syncs bidirectionally with React via useAgent(). The agent moves cards through tool calls; you click, edit, and reorder them in the UI. Both sides observe and react to the same state - no separate frontend store, no manual sync.

https://github.com/user-attachments/assets/47761912-d46a-4fb3-b9bd-cb41ddd02e34

Prerequisites

• Node.js 18+
• Python 3.8+
• uv (Python package manager)
• Any of the following package managers:
• npm (default)
• pnpm
• yarn
• bun
• OpenAI API Key (for the LangGraph agent)

Getting Started

1. Install dependencies (npm, or pnpm/yarn/bun):

npm install

This will also install the Python agent dependencies via uv sync.

2. Set up your environment variables:

cp .env.example .env

Then edit the .env file and add your OpenAI API key:

OPENAI_API_KEY=your-openai-api-key-here

3. Start the development server:

npm run dev

This will start both the UI and agent servers concurrently.

Available Scripts

The following scripts can also be run using your preferred package manager:

• dev - Starts both UI and agent servers in development mode
• dev:debug - Starts development servers with debug logging enabled
• dev:ui - Starts only the Next.js UI server
• dev:agent - Starts only the LangGraph agent server
• build - Builds the Next.js application for production
• start - Starts the production server
• install:agent - Installs Python dependencies for the agent

Project Structure

├── src/                         # Next.js frontend source
│   ├── app/
│   │   ├── page.tsx             # Main page
│   │   └── api/copilotkit/      # CopilotKit API route
│   ├── components/
│   │   ├── example-canvas/      # Todo list UI
│   │   ├── example-layout/      # Layout: chat + canvas side-by-side
│   │   └── generative-ui/       # Example generative UI components
│   └── hooks/
├── agent/                       # LangGraph Python agent
│   ├── main.py                  # Agent entry point
│   └── src/
│       ├── todos.py             # Todo tools and state schema
│       └── query.py             # Example data query tool
├── scripts/                     # Agent setup and run scripts
│   ├── setup-agent.sh / .bat
│   └── run-agent.sh / .bat
├── public/                      # Static assets
├── next.config.ts
├── tsconfig.json
└── package.json

A2UI - Agent-to-User Interface

This starter includes A2UI support, allowing the agent to generate rich, interactive UI surfaces declaratively. Instead of returning plain text, the agent sends a JSON description of the UI it wants to render, and the frontend turns it into real components.

How it works

A2UI uses three concepts:

1. Catalog - a set of component definitions (schema) paired with React renderers. Registered once in layout.tsx via <CopilotKitProvider a2ui={{ catalog: demonstrationCatalog }}>.
2. Surface - a rendered UI instance. The agent creates a surface, sets its components, and binds data to it.
3. Operations - the agent returns a2ui.render(operations=[...]) from a tool, which the middleware streams to the frontend.

Two patterns

Both patterns use the same catalog on the frontend - the difference is where the component tree comes from.

Key files

Adding a custom component

1. Define the component schema in definitions.ts:

MyWidget: {
  description: "A brief description for the agent.",
  props: z.object({ title: z.string(), value: z.number() }),
},

2. Render it in renderers.tsx:

MyWidget: ({ props }) => (
  <div>{props.title}: {props.value}</div>
),

Renderers are type-checked against the definitions - TypeScript will error if props don't match.

3. Use it from the agent. The component is automatically available to both fixed-schema templates and the dynamic-schema LLM.

Adding a new fixed-schema tool

1. Create a JSON schema file in agent/src/a2ui/schemas/ describing the component tree.
2. Create a Python tool that loads the schema with a2ui.load_schema() and returns a2ui.render(operations=[...]) with your data. See a2ui_fixed_schema.py for the pattern.

Showcase mode

showcase.json controls which suggestion pills are visually highlighted. Set "showcase": "a2ui" to highlight the A2UI demos, or "showcase": "default" for no highlights. This is configured automatically when scaffolding via npx copilotkit create --framework a2ui.

Further reading

• A2UI Specification
• CopilotKit A2UI Documentation

Documentation

• LangGraph Documentation - Learn more about LangGraph and its features
• CopilotKit Documentation - Explore CopilotKit's capabilities