Display components
Register React components that your agent can render in the chat.
Not available for Langchain DeepAgents yet
gen-ui-tool-based demo, and Langchain DeepAgents doesn't have it yet. See this page for CopilotKit's Built-in Agent, LangGraph (Python), LangGraph (TypeScript).What is this?
A display component is a React component that your agent can call as a tool. When the agent calls the tool, CopilotKit renders your component directly in the chat with the tool's arguments as props. You do not write a handler, and the user does not need to do anything.
import { useComponent } from "@copilotkit/react-core/v2";
import { Chart, ChartProps } from "./chart";
useComponent({
name: "showChart",
description: "Populate data and show the user a chart",
parameters: ChartProps,
render: Chart
});
When should I use this?
Use a display component when you want to:
- Display rich UI (cards, charts, tables) inline in the chat
- Show structured data from agent responses
- Render previews, status indicators, or visual feedback
- Let the agent present information beyond plain text
How it works in code
Wire CopilotKit middleware into your agent
Deep Agents compile to LangGraph graphs, and CopilotKitMiddleware is the
bridge. It reads the frontend tools from the request. It adds them to the
tool list that the model sees. Without the middleware, a tool that you
register with useFrontendTool or useComponent never reaches the model.
from deepagents import create_deep_agent
from copilotkit import CopilotKitMiddleware
agent = create_deep_agent(
model="openai:gpt-6-luna",
tools=[], # Backend tools go here
middleware=[CopilotKitMiddleware()],
system_prompt=SYSTEM_PROMPT,
)Without the middleware the run still completes, and the tool is never called, because the model was never told the tool exists. You do not write code to call a frontend tool: the middleware adds it to every model call, and the agent calls it like any other tool.
Tell the model when to call it
The forwarded tool arrives on every run, but a model with no instruction
about it will answer in prose and never call it. Name the tool in
system_prompt and say what it is for.
SYSTEM_PROMPT = """
You are a data visualization assistant.
When the user asks for a chart, call `render_bar_chart` with a concise
title and a `data` array of `{label, value}` items.
Keep chat responses brief and let the chart do the talking.
"""Register a tool in the browser
Deep Agents has no live demo on these pages yet, so the demo code below does not show for it. Here is a minimal frontend tool to start from. It says hello to the user:
import { z } from "zod";
import { useFrontendTool } from "@copilotkit/react-core/v2";
export function Page() {
// ...
useFrontendTool({
name: "sayHello",
description: "Say hello to the user",
parameters: z.object({
name: z.string().describe("The name of the user to say hello to"),
}),
handler: async ({ name }) => {
alert(`Hello, ${name}!`);
return `Said hello to ${name}!`;
},
});
// ...
}Ask the agent: Say hello to Ada. The browser shows an alert with
Hello, Ada!, and the agent replies after it gets the result.
The display component receives the tool's arguments as typed props and mounts inline in the chat. Below is the bar chart from the demo. The agent sends the data, and the component draws it.
Ask the agent for a chart, for example Show me a bar chart of quarterly sales for Q1, Q2, Q3, Q4. The chart renders in the chat with the data
that the agent filled in.
Without parameters
For simple components that don't need typed parameters, leave out
parameters. The component then accepts any props:
useComponent({
name: "showGreeting",
render: ({ message }: { message: string }) => (
<div className="rounded border p-3 bg-blue-50">
<p>{message}</p>
</div>
),
});Scoping to an agent
In multi-agent setups, pass agentId to scope a component to one agent:
useComponent({
name: "renderProfile",
parameters: z.object({ userId: z.string() }),
render: ProfileCard,
agentId: "support-agent",
});How is this guide?