Frontend Overview

Give your agents a user interface

CrewAI runs your agents. CopilotKit gives them a frontend. Together they let you build applications where users chat with a Crew or Flow, watch it work in real time, approve its decisions, and see its output rendered as live UI instead of walls of text. The two connect through the AG-UI protocol. The ag-ui-crewai package exposes any Crew or Flow as an AG-UI endpoint. CopilotKit’s React hooks and components consume that endpoint. This unlocks experiences that go well beyond a chat box:

Generative UI

Render agent tool calls and state as your own React components.

Human-in-the-Loop

Pause the agent to collect user approval or input mid-run.

Shared State

Keep agent state and your app UI in two-way sync.

Channels

Run the same agent as a Slack, Discord, or Teams bot.

This guide gets a Crew or Flow talking to a Next.js frontend end to end. The rest of the section builds on the app you set up here.

Architecture

There are three pieces:

CrewAI agent server — a Python process that serves your Crew or Flow over AG-UI (FastAPI + ag-ui-crewai).
CopilotKit runtime — a Next.js route that registers your agent and proxies requests to it.
React frontend — the <CopilotKit> provider plus chat and generative-UI components.

React app  ──►  CopilotKit runtime (/api/copilotkit)  ──►  CrewAI server (AG-UI)  ──►  Crew / Flow

This guide covers the self-hosted path: you run the CrewAI agent server yourself with ag-ui-crewai, and it works locally with no managed service. CopilotKit also offers a managed path (CopilotKit Cloud / Enterprise Intelligence) with hosted threads and an inspector — see the CopilotKit CrewAI quickstart if you want that instead. The frontend code in this section is the same either way; only how the agent is hosted and registered differs.

CrewAI runs behind AG-UI in three shapes: regular Flows (used throughout these guides), Conversational Flows (native, session-aware, turn-based, at full feature parity), and Crews (basic chat). The frontend in this section is identical across them — only the backend authoring and registration differ.

Integration guide

Serve your agent over AG-UI

Install the integration package into your CrewAI project:

pip install ag-ui-crewai

Expose your agent from a FastAPI app. Flows use add_crewai_flow_fastapi_endpoint; Crews use add_crewai_crew_fastapi_endpoint. You can register as many as you want, each on its own path.

# server.py
from fastapi import FastAPI
from ag_ui_crewai.endpoint import add_crewai_flow_fastapi_endpoint
from my_agents.recipe_flow import RecipeFlow

app = FastAPI(title="CrewAI Agent Server")

add_crewai_flow_fastapi_endpoint(
    app=app,
    flow=RecipeFlow(),
    path="/recipe",
)

# server.py
from fastapi import FastAPI
from ag_ui_crewai.endpoint import add_crewai_crew_fastapi_endpoint
from my_agents.research_crew import ResearchCrew

app = FastAPI(title="CrewAI Agent Server")

add_crewai_crew_fastapi_endpoint(
    app=app,
    crew=ResearchCrew().crew(),
    path="/research",
)

Run it:

uvicorn server:app --port 8000

Set the environment variables for your LLM provider (for example OPENAI_API_KEY) before starting the server.

Create a Next.js app

If you do not have a frontend yet, scaffold one:

npx create-next-app@latest my-app
cd my-app

Install CopilotKit and the CrewAI AG-UI client:

npm install @copilotkit/react-core @copilotkit/react-ui @copilotkit/runtime @ag-ui/crewai

Add the CopilotKit runtime

Create a route that registers your CrewAI agent(s) with the CopilotKit runtime. Each agent points at a path on your Python server via CrewAIAgent.

// app/api/copilotkit/route.ts
import {
  CopilotRuntime,
  InMemoryAgentRunner,
  createCopilotEndpoint,
} from "@copilotkit/runtime/v2";
import { CrewAIAgent } from "@ag-ui/crewai";
import { handle } from "hono/vercel";

const runtime = new CopilotRuntime({
  agents: {
    recipe: new CrewAIAgent({ url: "http://localhost:8000/recipe" }),
  },
  runner: new InMemoryAgentRunner(),
});

const app = createCopilotEndpoint({
  runtime,
  basePath: "/api/copilotkit",
});

const handler = handle(app);
export const GET = handler;
export const POST = handler;

Wrap your app with the provider

Point <CopilotKit> at the runtime route and name the agent you registered.

// app/page.tsx
"use client";
import { CopilotKit } from "@copilotkit/react-core";
import { CopilotSidebar } from "@copilotkit/react-core/v2";
import "@copilotkit/react-core/v2/styles.css";

export default function Page() {
  return (
    <CopilotKit runtimeUrl="/api/copilotkit" agent="recipe">
      <YourApp />
      <CopilotSidebar agentId="recipe" labels={{ modalHeaderTitle: "Assistant" }} />
    </CopilotKit>
  );
}

Run it

Start both processes and open the app. Chatting in the sidebar now runs your Crew or Flow.

uvicorn server:app --port 8000   # terminal 1
npm run dev                       # terminal 2

Chat UI options

CopilotKit ships three interchangeable chat surfaces. Swap the component; the wiring is identical.

import { CopilotSidebar } from "@copilotkit/react-core/v2";

<CopilotSidebar agentId="recipe" />

import { CopilotPopup } from "@copilotkit/react-core/v2";

<CopilotPopup agentId="recipe" />

import { CopilotChat } from "@copilotkit/react-core/v2";

<CopilotChat agentId="recipe" />

Where to go next

Generative UI

Render tool calls and agent state as custom components.

Frontend Actions

Let the agent call functions that run in the browser.

Human-in-the-Loop

Gate agent actions behind user approval.

Predictive State

Stream in-progress state to the UI as the agent works.

Get Started

Guides

Core Concepts

MCP Integration

Tools

Observability

Learn

Telemetry

Frontend Overview

Give your agents a user interface

Generative UI

Human-in-the-Loop

Shared State

Channels

Architecture

Integration guide

Chat UI options

Where to go next

Generative UI

Frontend Actions

Human-in-the-Loop

Predictive State

​Give your agents a user interface

Generative UI

Human-in-the-Loop

Shared State

Channels

​Architecture

​Integration guide

​Chat UI options

​Where to go next

Generative UI

Frontend Actions

Human-in-the-Loop

Predictive State

Give your agents a user interface

Architecture

Integration guide

Chat UI options

Where to go next