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
Add a stub for each frontend tool
The LlamaIndex AG-UI router (llama_index.protocols.ag_ui) gives the
model only the tools you pass to get_ag_ui_workflow_router. It does not
read the tool list CopilotKit sends with each run. So a tool registered
with useFrontendTool, useComponent, or useHumanInTheLoop reaches the
model only when frontend_tools holds a stub with the same name and
arguments.
from typing import Annotated
from llama_index.llms.openai import OpenAI
from llama_index.protocols.ag_ui.router import get_ag_ui_workflow_router
def change_background(
background: Annotated[str, "CSS background value. Prefer gradients."],
) -> str:
"""Change the background color/gradient of the chat area."""
return f"Background changed to {background}"
agentic_chat_router = get_ag_ui_workflow_router(
llm=OpenAI(model="gpt-6-luna"),
frontend_tools=[change_background],
system_prompt=(
"You are a helpful assistant. "
"Change the UI background when asked (via frontend tool)."
),
)The browser runs the tool, so the stub body is never called. A missing stub fails quietly: the model never sees the tool and answers in prose.
Tell the model when to call it
Even with the stub in place, a model with no instruction about the tool
tends to answer in prose. Name the tool in system_prompt and say what it
is for.
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.
How is this guide?