agents-sdk

작성자: Cloudflare

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.

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Your knowledge of the Agents SDK may be outdated.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

Cloudflare의 다른 스킬

building-ai-agent-on-cloudflare
Cloudflare
| Cloudflare에서 Agents SDK를 사용하여 상태 관리, 실시간 WebSocket, 예약 작업, 도구 통합 및 채팅 기능을 갖춘 AI 에이전트를 구축합니다. Workers에 배포되는 프로덕션 준비 에이전트 코드를 생성합니다. 사용 시기: 사용자가 "에이전트 구축", "AI 에이전트", "채팅 에이전트", "상태 저장 에이전트"를 원하거나, "Agents SDK"를 언급하거나, "실시간 AI", "WebSocket AI"가 필요하거나, 에이전트 "상태 관리", "예약 작업" 또는 "도구 호출"에 대해 질문할 때.
developmentofficial
building-mcp-server-on-cloudflare
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".
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
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.
official
sandbox-sdk
Cloudflare
샌드박스 애플리케이션을 구축하여 안전한 코드 실행을 지원합니다. AI 코드 실행, 코드 인터프리터, CI/CD 시스템, 대화형 개발 환경을 구축하거나 신뢰할 수 없는 코드를 실행할 때 로드하세요. Sandbox SDK 수명 주기, 명령어, 파일, 코드 인터프리터 및 미리보기 URL을 다룹니다.
official
web-perf
Cloudflare
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed.
official
workers-best-practices
Cloudflare
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
official
wrangler
Cloudflare
Cloudflare Workers CLI를 사용하여 Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines 및 Secrets Store를 배포, 개발 및 관리할 수 있습니다. wrangler 명령어를 실행하기 전에 로드하여 올바른 구문과 모범 사례를 준수하세요.
official