agents-sdk

Bangun agen AI di Cloudflare Workers menggunakan Agents SDK. Muat saat membuat agen stateful, alur kerja tahan lama, aplikasi WebSocket real-time, tugas terjadwal, server MCP, atau aplikasi obrolan. Mencakup kelas Agent, manajemen status, RPC yang dapat dipanggil, integrasi Workflows, dan React hooks.

npx skills add https://github.com/cloudflare/skills --skill agents-sdk

Cloudflare Agents SDK

Your knowledge of the Agents SDK may be outdated.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

Retrieval Sources

Cloudflare docs: https://developers.cloudflare.com/agents/

TopicDocs URLUse for
Getting startedQuick startFirst agent, project setup
Adding to existing projectAdd to existing projectInstall into existing Workers app
ConfigurationConfigurationwrangler.jsonc, bindings, assets, deployment
Agent classAgents APIAgent lifecycle, patterns, pitfalls
StateStore and sync statesetState, validateStateChange, persistence
RoutingRoutingURL patterns, routeAgentRequest
Callable methodsCallable methods@callable, RPC, streaming, timeouts
SchedulingSchedule tasksschedule(), scheduleEvery(), cron
WorkflowsRun workflowsAgentWorkflow, durable multi-step tasks
HTTP/WebSocketsWebSocketsLifecycle hooks, hibernation
Chat agentsChat agentsAIChatAgent, streaming, tools, persistence
Client SDKClient SDKuseAgent, useAgentChat, React hooks
Client toolsClient toolsClient-side tools, autoContinueAfterToolResult
Server-driven messagesTrigger patternssaveMessages, waitUntilStable, server-initiated turns
Resumable streamingResumable streamingStream recovery on disconnect
EmailEmailEmail routing, secure reply resolver
MCP clientMCP clientConnecting to MCP servers
MCP serverMCP serverBuilding MCP servers with McpAgent
MCP transportsMCP transportsStreamable HTTP, SSE, RPC transport options
Securing MCP serversSecuring MCPOAuth, proxy MCP, hardening
Human-in-the-loopHuman-in-the-loopApproval flows, needsApproval, workflows
Durable executionDurable executionrunFiber(), stash(), surviving DO eviction
QueueQueueBuilt-in FIFO queue, queue()
RetriesRetriesthis.retry(), backoff/jitter
ObservabilityObservabilityDiagnostics-channel events
Push notificationsPush notificationsWeb Push + VAPID from agents
WebhooksWebhooksReceiving external webhooks
Cross-domain authCross-domain authWebSocket auth, tokens, CORS
Readonly connectionsReadonlyshouldConnectionBeReadonly
VoiceVoiceExperimental STT/TTS, withVoice
Browse the webBrowser toolsExperimental CDP browser automation
ThinkThinkExperimental higher-level chat agent class
MigrationsAI SDK v5, AI SDK v6Upgrading @cloudflare/ai-chat

Capabilities

The Agents SDK provides:

  • Persistent state — SQLite-backed, auto-synced to clients via setState
  • Callable RPC@callable() methods invoked over WebSocket
  • Scheduling — One-time, recurring (scheduleEvery), and cron tasks
  • Workflows — Durable multi-step background processing via AgentWorkflow
  • Durable executionrunFiber() / stash() for work that survives DO eviction
  • Queue — Built-in FIFO queue with retries via queue()
  • Retriesthis.retry() with exponential backoff and jitter
  • MCP integration — Connect to MCP servers or build your own with McpAgent
  • Email handling — Receive and reply to emails with secure routing
  • Streaming chatAIChatAgent with resumable streams, message persistence, tools
  • Server-driven messagessaveMessages, waitUntilStable for proactive agent turns
  • React hooksuseAgent, useAgentChat for client apps
  • Observabilitydiagnostics_channel events for state, RPC, schedule, lifecycle
  • Push notifications — Web Push + VAPID delivery from agents
  • Webhooks — Receive and verify external webhooks
  • Voice (experimental) — STT/TTS via @cloudflare/voice
  • Browser tools (experimental) — CDP-powered browsing via agents/browser
  • Think (experimental) — Higher-level chat agent via @cloudflare/think

FIRST: Verify Installation

npm ls agents  # Should show agents package

If not installed:

npm install agents

For chat agents:

npm install agents @cloudflare/ai-chat ai @ai-sdk/react

Wrangler Configuration

{
  "compatibility_flags": ["nodejs_compat"],
  "durable_objects": {
    "bindings": [{ "name": "MyAgent", "class_name": "MyAgent" }]
  },
  "migrations": [{ "tag": "v1", "new_sqlite_classes": ["MyAgent"] }]
}

Gotchas:

  • Do NOT enable experimentalDecorators in tsconfig (breaks @callable)
  • Never edit old migrations — always add new tags
  • Each agent class needs its own DO binding + migration entry
  • Add "ai": { "binding": "AI" } for Workers AI

Agent Class

import { Agent, routeAgentRequest, callable } from "agents";

type State = { count: number };

export class Counter extends Agent<Env, State> {
  initialState = { count: 0 };

  validateStateChange(nextState: State, source: Connection | "server") {
    if (nextState.count < 0) throw new Error("Count cannot be negative");
  }

  onStateUpdate(state: State, source: Connection | "server") {
    console.log("State updated:", state);
  }

  @callable()
  increment() {
    this.setState({ count: this.state.count + 1 });
    return this.state.count;
  }
}

export default {
  fetch: (req, env) => routeAgentRequest(req, env) ?? new Response("Not found", { status: 404 })
};

Routing

Requests route to /agents/{agent-name}/{instance-name}:

ClassURL
Counter/agents/counter/user-123
ChatRoom/agents/chat-room/lobby

Client: useAgent({ agent: "Counter", name: "user-123" })

Custom routing: use getAgentByName(env.MyAgent, "instance-id") then agent.fetch(request).

Core APIs

TaskAPI
Read statethis.state.count
Write statethis.setState({ count: 1 })
SQL querythis.sql`SELECT * FROM users WHERE id = ${id}`
Schedule (delay)await this.schedule(60, "task", payload)
Schedule (cron)await this.schedule("0 * * * *", "task", payload)
Schedule (interval)await this.scheduleEvery(30, "poll")
RPC method@callable() myMethod() { ... }
Streaming RPC@callable({ streaming: true }) stream(res) { ... }
Start workflowawait this.runWorkflow("ProcessingWorkflow", params)
Durable fiberawait this.runFiber("name", async (ctx) => { ... })
Enqueue workthis.queue("handler", payload)
Retry with backoffawait this.retry(fn, { maxAttempts: 5 })
Broadcast to clientsthis.broadcast(message)
Get connectionsthis.getConnections(tag?)

React Client

import { useAgent } from "agents/react";

function App() {
  const [state, setLocalState] = useState({ count: 0 });

  const agent = useAgent({
    agent: "Counter",
    name: "my-instance",
    onStateUpdate: (newState) => setLocalState(newState),
    onIdentity: (name, agentType) => console.log(`Connected to ${name}`)
  });

  return (
    <button onClick={() => agent.setState({ count: state.count + 1 })}>
      Count: {state.count}
    </button>
  );
}

References

Core

Chat & Streaming

Background Processing

Integrations

Experimental

Lebih banyak skill dari Cloudflare

building-ai-agent-on-cloudflare
Cloudflare
Membangun agen AI di Cloudflare menggunakan Agents SDK dengan manajemen status, WebSocket waktu nyata, tugas terjadwal, integrasi alat, dan kemampuan obrolan. Menghasilkan kode agen siap produksi yang di-deploy ke Workers. Gunakan ketika: pengguna ingin "membangun agen", "agen AI", "agen obrolan", "agen stateful", menyebut "Agents SDK", membutuhkan "AI waktu nyata", "WebSocket AI", atau bertanya tentang "manajemen status" agen, "tugas terjadwal", atau "pemanggilan alat".
developmentofficial
building-mcp-server-on-cloudflare
Cloudflare
Membangun server MCP (Model Context Protocol) jarak jauh di Cloudflare Workers dengan alat, autentikasi OAuth, dan deployment produksi. Menghasilkan kode server, mengonfigurasi penyedia autentikasi, dan melakukan deployment ke Workers. Gunakan ketika: pengguna ingin "membangun server MCP", "membuat alat MCP", "MCP jarak jauh", "deploy MCP", menambahkan "OAuth ke MCP", atau menyebutkan Model Context Protocol di Cloudflare. Juga terpicu pada "autentikasi MCP" atau "deployment MCP".
developmentofficial
cloudflare
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. references: - workers - pages - d1 - durable-objects - workers-ai
official
durable-objects
Cloudflare
Buat dan tinjau Cloudflare Durable Objects. Gunakan saat membangun koordinasi stateful (ruang obrolan, game multipemain, sistem pemesanan), mengimplementasikan metode RPC, penyimpanan SQLite, alarm, WebSocket, atau meninjau kode DO untuk praktik terbaik. Mencakup integrasi Workers, konfigurasi wrangler, dan pengujian dengan Vitest.
official
sandbox-sdk
Cloudflare
Bangun aplikasi sandbox untuk eksekusi kode yang aman. Muat saat membangun eksekusi kode AI, interpreter kode, sistem CI/CD, lingkungan pengembangan interaktif, atau mengeksekusi kode yang tidak tepercaya. Mencakup siklus hidup Sandbox SDK, perintah, file, interpreter kode, dan URL pratinjau.
official
web-perf
Cloudflare
Menganalisis kinerja web menggunakan Chrome DevTools MCP. Mengukur Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), mengidentifikasi sumber daya yang memblokir rendering, rantai ketergantungan jaringan, pergeseran tata letak, masalah caching, dan celah aksesibilitas. Gunakan saat diminta untuk mengaudit, memprofilkan, men-debug, atau mengoptimalkan kinerja pemuatan halaman, skor Lighthouse, atau kecepatan situs.
official
workers-best-practices
Cloudflare
Meninjau dan menulis kode Cloudflare Workers sesuai praktik terbaik produksi. Muat saat menulis Workers baru, meninjau kode Worker, mengonfigurasi wrangler.jsonc, atau memeriksa anti-pola Workers umum (streaming, janji mengambang, status global, rahasia, binding, observabilitas). Lebih mengutamakan pengambilan dari dokumentasi Cloudflare daripada pengetahuan terlatih.
official
wrangler
Cloudflare
CLI Cloudflare Workers untuk men-deploy, mengembangkan, dan mengelola Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, dan Secrets Store. Muat sebelum menjalankan perintah wrangler untuk memastikan sintaksis dan praktik terbaik yang benar.
official