Agent skill

building-ai-agent-on-cloudflare

Builds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities. Generates production-ready agent code deployed to Workers. Use when: user wants to "build an agent", "AI agent", "chat agent", "stateful agent", mentions "Agents SDK", needs "real-time AI", "WebSocket AI", or asks about agent "state management", "scheduled tasks", or "tool calling". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Stars 766
Forks 85

Install this agent skill to your Project

npx add-skill https://github.com/cloudflare/skills/tree/main/skills/building-ai-agent-on-cloudflare

SKILL.md

Building Cloudflare Agents

Your knowledge of the Agents SDK may be outdated. Prefer retrieval over pre-training for any agent-building task.

Retrieval Sources

Source How to retrieve Use for
Agents SDK docs https://github.com/cloudflare/agents/tree/main/docs SDK API, state, routing, scheduling
Cloudflare Agents docs https://developers.cloudflare.com/agents/ Platform integration, deployment
Workers docs Search tool or https://developers.cloudflare.com/workers/ Runtime APIs, bindings, config

When to Use

  • User wants to build an AI agent or chatbot
  • User needs stateful, real-time AI interactions
  • User asks about the Cloudflare Agents SDK
  • User wants scheduled tasks or background AI work
  • User needs WebSocket-based AI communication

Prerequisites

  • Cloudflare account with Workers enabled
  • Node.js 18+ and npm/pnpm/yarn
  • Wrangler CLI (npm install -g wrangler)

Quick Start

bash
npm create cloudflare@latest -- my-agent --template=cloudflare/agents-starter
cd my-agent
npm start

Agent runs at http://localhost:8787

Core Concepts

What is an Agent?

An Agent is a stateful, persistent AI service that:

  • Maintains state across requests and reconnections
  • Communicates via WebSockets or HTTP
  • Runs on Cloudflare's edge via Durable Objects
  • Can schedule tasks and call tools
  • Scales horizontally (each user/session gets own instance)

Agent Lifecycle

Client connects → Agent.onConnect() → Agent processes messages
                                    → Agent.onMessage()
                                    → Agent.setState() (persists + syncs)
Client disconnects → State persists → Client reconnects → State restored

Basic Agent Structure

typescript
import { Agent, Connection } from "agents";

interface Env {
  AI: Ai;  // Workers AI binding
}

interface State {
  messages: Array<{ role: string; content: string }>;
  preferences: Record<string, string>;
}

export class MyAgent extends Agent<Env, State> {
  // Initial state for new instances
  initialState: State = {
    messages: [],
    preferences: {},
  };

  // Called when agent starts or resumes
  async onStart() {
    console.log("Agent started with state:", this.state);
  }

  // Handle WebSocket connections
  async onConnect(connection: Connection) {
    connection.send(JSON.stringify({
      type: "welcome",
      history: this.state.messages,
    }));
  }

  // Handle incoming messages
  async onMessage(connection: Connection, message: string) {
    const data = JSON.parse(message);

    if (data.type === "chat") {
      await this.handleChat(connection, data.content);
    }
  }

  // Handle disconnections
  async onClose(connection: Connection) {
    console.log("Client disconnected");
  }

  // React to state changes
  onStateUpdate(state: State, source: string) {
    console.log("State updated by:", source);
  }

  private async handleChat(connection: Connection, userMessage: string) {
    // Add user message to history
    const messages = [
      ...this.state.messages,
      { role: "user", content: userMessage },
    ];

    // Call AI
    const response = await this.env.AI.run("@cf/meta/llama-3-8b-instruct", {
      messages,
    });

    // Update state (persists and syncs to all clients)
    this.setState({
      ...this.state,
      messages: [
        ...messages,
        { role: "assistant", content: response.response },
      ],
    });

    // Send response
    connection.send(JSON.stringify({
      type: "response",
      content: response.response,
    }));
  }
}

Entry Point Configuration

typescript
// src/index.ts
import { routeAgentRequest } from "agents";
import { MyAgent } from "./agent";

export default {
  async fetch(request: Request, env: Env) {
    // routeAgentRequest handles routing to /agents/:class/:name
    return (
      (await routeAgentRequest(request, env)) ||
      new Response("Not found", { status: 404 })
    );
  },
};

export { MyAgent };

Clients connect via: wss://my-agent.workers.dev/agents/MyAgent/session-id

Wrangler Configuration

jsonc
{
  "name": "my-agent",
  "main": "src/index.ts",
  "compatibility_date": "2024-12-01",
  "ai": { "binding": "AI" },
  "durable_objects": {
    "bindings": [{ "name": "MyAgent", "class_name": "MyAgent" }]
  },
  "migrations": [{ "tag": "v1", "new_sqlite_classes": ["MyAgent"] }]
}

State Management

Reading State

typescript
// Current state is always available
const currentMessages = this.state.messages;
const userPrefs = this.state.preferences;

Updating State

typescript
// setState persists AND syncs to all connected clients
this.setState({
  ...this.state,
  messages: [...this.state.messages, newMessage],
});

// Partial updates work too
this.setState({
  preferences: { ...this.state.preferences, theme: "dark" },
});

SQL Storage

For complex queries, use the embedded SQLite database:

typescript
// Create tables
await this.sql`
  CREATE TABLE IF NOT EXISTS documents (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    title TEXT NOT NULL,
    content TEXT,
    created_at DATETIME DEFAULT CURRENT_TIMESTAMP
  )
`;

// Insert
await this.sql`
  INSERT INTO documents (title, content)
  VALUES (${title}, ${content})
`;

// Query
const docs = await this.sql`
  SELECT * FROM documents WHERE title LIKE ${`%${search}%`}
`;

Scheduled Tasks

Agents can schedule future work:

typescript
async onMessage(connection: Connection, message: string) {
  const data = JSON.parse(message);

  if (data.type === "schedule_reminder") {
    // Schedule task for 1 hour from now
    const { id } = await this.schedule(3600, "sendReminder", {
      message: data.reminderText,
      userId: data.userId,
    });

    connection.send(JSON.stringify({ type: "scheduled", taskId: id }));
  }
}

// Called when scheduled task fires
async sendReminder(data: { message: string; userId: string }) {
  // Send notification, email, etc.
  console.log(`Reminder for ${data.userId}: ${data.message}`);

  // Can also update state
  this.setState({
    ...this.state,
    lastReminder: new Date().toISOString(),
  });
}

Schedule Options

typescript
// Delay in seconds
await this.schedule(60, "taskMethod", { data });

// Specific date
await this.schedule(new Date("2025-01-01T00:00:00Z"), "taskMethod", { data });

// Cron expression (recurring)
await this.schedule("0 9 * * *", "dailyTask", {});  // 9 AM daily
await this.schedule("*/5 * * * *", "everyFiveMinutes", {});  // Every 5 min

// Manage schedules
const schedules = await this.getSchedules();
await this.cancelSchedule(taskId);

Chat Agent (AI-Powered)

For chat-focused agents, extend AIChatAgent:

typescript
import { AIChatAgent } from "agents/ai-chat-agent";

export class ChatBot extends AIChatAgent<Env> {
  // Called for each user message
  async onChatMessage(message: string) {
    const response = await this.env.AI.run("@cf/meta/llama-3-8b-instruct", {
      messages: [
        { role: "system", content: "You are a helpful assistant." },
        ...this.messages,  // Automatic history management
        { role: "user", content: message },
      ],
      stream: true,
    });

    // Stream response back to client
    return response;
  }
}

Features included:

  • Automatic message history
  • Resumable streaming (survives disconnects)
  • Built-in saveMessages() for persistence

Client Integration

React Hook

tsx
import { useAgent } from "agents/react";

function Chat() {
  const { state, send, connected } = useAgent({
    agent: "my-agent",
    name: userId,  // Agent instance ID
  });

  const sendMessage = (text: string) => {
    send(JSON.stringify({ type: "chat", content: text }));
  };

  return (
    <div>
      {state.messages.map((msg, i) => (
        <div key={i}>{msg.role}: {msg.content}</div>
      ))}
      <input onKeyDown={(e) => e.key === "Enter" && sendMessage(e.target.value)} />
    </div>
  );
}

Vanilla JavaScript

javascript
const ws = new WebSocket("wss://my-agent.workers.dev/agents/MyAgent/user123");

ws.onopen = () => {
  console.log("Connected to agent");
};

ws.onmessage = (event) => {
  const data = JSON.parse(event.data);
  console.log("Received:", data);
};

ws.send(JSON.stringify({ type: "chat", content: "Hello!" }));

Common Patterns

See references/agent-patterns.md for:

  • Tool calling and function execution
  • Multi-agent orchestration
  • RAG (Retrieval Augmented Generation)
  • Human-in-the-loop workflows

Deployment

bash
# Deploy
npx wrangler deploy

# View logs
wrangler tail

# Test endpoint
curl https://my-agent.workers.dev/agents/MyAgent/test-user

Troubleshooting

See references/troubleshooting.md for common issues.

References

  • references/examples.md — Official templates and production examples
  • references/agent-patterns.md — Advanced patterns
  • references/state-patterns.md — State management strategies
  • references/troubleshooting.md — Error solutions

Expand your agent's capabilities with these related and highly-rated skills.

cloudflare/skills

wrangler

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

766 85
Explore
cloudflare/skills

building-mcp-server-on-cloudflare

Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code, configures auth providers, and deploys to Workers. Use when: user wants to "build MCP server", "create MCP tools", "remote MCP", "deploy MCP", add "OAuth to MCP", or mentions Model Context Protocol on Cloudflare. Also triggers on "MCP authentication" or "MCP deployment". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

766 85
Explore
cloudflare/skills

cloudflare

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

766 85
Explore
cloudflare/skills

durable-objects

Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

766 85
Explore
cloudflare/skills

agents-sdk

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

766 85
Explore
cloudflare/skills

sandbox-sdk

Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

766 85
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results