Frontend Tools
Let your agent interact with and update your application's UI.
See this in Inspector
Open Inspector on localhost. Go to Inspect, then Frontend Tools. Your tool and its schema are listed.
More detail: Inspector.
What is this?
A frontend tool is a function that you register in the browser. Your agent can call it, and the function runs in the user's browser. Because the handler runs in the browser, it has direct access to component state, browser APIs, and any third-party UI library the page already uses. That's how an agent can "reach into" the app: update React state, trigger animations, read localStorage, pop a toast, or steer the user's view.
This page covers the "agent drives the UI" shape of frontend tools. To render a component for a tool call, see Generative UI. To ask the user before a tool runs, see Human-in-the-loop.
When should I use this?
Use frontend tools when your agent needs to:
- Read or modify React component state
- Access browser APIs like
localStorage,sessionStorage, or cookies - Trigger UI updates, animations, or transitions
- Show alerts, toasts, or notifications
- Interact with third-party frontend libraries
How it works in code
Nothing to wire in config mode
A BuiltInAgent built from configuration merges the request's tool
definitions into the tool list it hands the model, so the agent declares
none of its own. A tool registered with useFrontendTool, or a component
registered with useComponent, reaches the model by name with no extra
wiring.
import { BuiltInAgent } from "@copilotkit/runtime/v2";
const builtInAgent = new BuiltInAgent({
model: "openai:gpt-6-luna",
prompt: SYSTEM_PROMPT,
});Keep the useComponent name distinct from every tool in config.tools.
The runtime layers the configured tools over the forwarded ones, so a
shared name resolves to the backend tool and the component never renders.
In factory mode you pass the tools yourself
A factory owns the model call, so BuiltInAgent ignores config.tools and
forwards nothing on your behalf. Read the tools off input and pass them
to the model, or the component never renders.
import {
BuiltInAgent,
convertMessagesToVercelAISDKMessages,
convertToolsToVercelAITools,
} from "@copilotkit/runtime/v2";
import { openai } from "@ai-sdk/openai";
import { streamText } from "ai";
const agent = new BuiltInAgent({
type: "aisdk",
factory: ({ input, abortSignal }) =>
streamText({
model: openai("gpt-6-luna"),
messages: convertMessagesToVercelAISDKMessages(input.messages),
tools: convertToolsToVercelAITools(input.tools),
abortSignal,
}),
});The factory owns precedence here. Nothing merges the two lists for you, so
a backend tool and a useComponent registration that share a name is your
conflict to resolve. Keep the names distinct.
Tell the model when to call it
This is the part that is easy to miss. The 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 the prompt and say what it is for.
export const 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.
If the user names a subject but supplies no numbers, invent plausible
sample values and render the chart on the first turn. Never reply with a
clarifying question asking for the data.`;Register a frontend tool with useFrontendTool. Give it a name, a Zod schema for parameters, and a handler. The agent can then call it like any other tool and your frontend runs it in the browser.
import React, { useState } from "react";
import {
CopilotKit,
CopilotSidebar,
useFrontendTool,
} from "@copilotkit/react-core/v2";
import { z } from "zod";
import { Background, DEFAULT_BACKGROUND } from "./background";
import { useFrontendToolsSuggestions } from "./suggestions";
function Chat() {
const [background, setBackground] = useState<string>(DEFAULT_BACKGROUND);
useFrontendTool({
name: "change_background",
description:
"Change the page background. Accepts any valid CSS background value — colors, linear or radial gradients, etc.",
parameters: z.object({
background: z
.string()
.describe("The CSS background value. Prefer gradients."),
}),
handler: async ({ background }) => {
setBackground(background);
return { status: "success" };
},
});The handler receives the parsed, type-safe parameters and can do anything the browser can: update state, call an API, touch the DOM. Its return value is sent back to the agent as the tool result so the model can reason about what happened.
handler: async ({ background }) => {
setBackground(background);
return { status: "success" };
},Ask the agent to change the background to a blue gradient. The page background changes, and the agent gets { status: "success" } as the tool result.
Registering a list of tools
useFrontendTool registers one tool per call, so it cannot be called in a loop
over a list whose length changes between renders. When the set of tools comes
from state, from props, or from a backend response, use
useFrontendTools instead. It takes an
array and runs a single effect over it, so the array can be empty on one render
and hold twenty entries on the next.
useFrontendTools(
reports.map((report) => ({
name: `open_${report.id}`,
description: `Open the ${report.title} report`,
handler: async () => navigate(`/reports/${report.id}`),
})),
[navigate],
);On each render:
- A tool that leaves the array is unregistered.
- A tool that joins the array is registered.
- A re-render that produces an equal list does not re-register anything.
A description built from your data stays current on its own. The second argument
is for values a handler closes over, such as navigate above.
Choose your AI backend
LangGraph (Python)
LangGraph (TypeScript)
LangGraph (FastAPI)
Langchain DeepAgents
Google ADK
Mastra
CrewAI Flows
PydanticAI
Google Antigravity
OpenAI Agents SDK (Python)
Claude Agent SDK (Python)
Claude Agent SDK (TypeScript)
Agno
AG2
LlamaIndex
AWS Strands (Python)
AWS Strands (TypeScript)
MS Agent Framework (Python)
MS Agent Framework (.NET)
MS Agent Harness (.NET)
How is this guide?