agents-sdk

Construa agentes de IA no Cloudflare Workers usando o Agents SDK. Carregue ao criar agentes com estado, fluxos de trabalho duráveis, aplicativos WebSocket em tempo real, tarefas agendadas, servidores MCP ou aplicativos de chat. Abrange a classe Agent, gerenciamento de estado, RPC chamável, integração com Workflows e hooks React.

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Your knowledge of the Agents SDK may be outdated.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

Mais skills de Cloudflare

building-ai-agent-on-cloudflare
Cloudflare
Constrói agentes de IA na Cloudflare usando o Agents SDK com gerenciamento de estado, WebSockets em tempo real, tarefas agendadas, integração de ferramentas e capacidades de chat. Gera código de agente pronto para produção implantado em Workers. Use quando: o usuário quiser "construir um agente", "agente de IA", "agente de chat", "agente com estado", mencionar "Agents SDK", precisar de "IA em tempo real", "WebSocket de IA", ou perguntar sobre "gerenciamento de estado" do agente, "tarefas agendadas" ou "chamada de ferramentas".
developmentofficial
building-mcp-server-on-cloudflare
Cloudflare
Constrói servidores MCP (Model Context Protocol) remotos no Cloudflare Workers com ferramentas, autenticação OAuth e implantação em produção. Gera código do servidor, configura provedores de autenticação e faz deploy nos Workers. Use quando: o usuário quiser "construir servidor MCP", "criar ferramentas MCP", "MCP remoto", "implantar MCP", adicionar "OAuth ao MCP" ou mencionar Model Context Protocol no Cloudflare. Também ativa em "autenticação MCP" ou "implantação 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
Criar e revisar Durable Objects do Cloudflare. Use ao construir coordenação com estado (salas de chat, jogos multiplayer, sistemas de reserva), implementar métodos RPC, armazenamento SQLite, alarmes, WebSockets ou revisar código DO para melhores práticas. Abrange integração com Workers, configuração do wrangler e testes com Vitest.
official
sandbox-sdk
Cloudflare
Construa aplicações em sandbox para execução segura de código. Carregue ao construir execução de código por IA, interpretadores de código, sistemas de CI/CD, ambientes de desenvolvimento interativos ou ao executar código não confiável. Abrange o ciclo de vida do Sandbox SDK, comandos, arquivos, interpretador de código e URLs de pré-visualização.
official
web-perf
Cloudflare
Analisa o desempenho web usando o Chrome DevTools MCP. Mede os Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifica recursos que bloqueiam a renderização, cadeias de dependência de rede, mudanças de layout, problemas de cache e lacunas de acessibilidade. Use quando solicitado a auditar, perfilar, depurar ou otimizar o desempenho de carregamento de páginas, pontuações do Lighthouse ou velocidade do site.
official
workers-best-practices
Cloudflare
Revisa e orienta o código do Cloudflare Workers de acordo com as melhores práticas de produção. Carregue ao escrever novos Workers, revisar código de Workers, configurar o wrangler.jsonc ou verificar anti-padrões comuns de Workers (streaming, promessas soltas, estado global, segredos, bindings, observabilidade). Prioriza a recuperação da documentação do Cloudflare em vez do conhecimento pré-treinado.
official
wrangler
Cloudflare
CLI do Cloudflare Workers para implantar, desenvolver e gerenciar Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines e Secrets Store. Carregue antes de executar comandos wrangler para garantir sintaxe correta e melhores práticas.
official