
agents-sdk
โ Officialโ 2,060by Cloudflare ยท part of cloudflare/skills
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, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
This is the playbook your agent receives when the skill activates โ you don't need to read it to use the skill, but it's here to audit before installing.
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Your knowledge of the Agents SDK may be outdated.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/
| Topic | Docs URL | Use for |
|---|---|---|
| Getting started | Quick start | First agent, project setup |
| Adding to existing project | Add to existing project | Install into existing Workers app |
| Configuration | Configuration | wrangler.jsonc, bindings, assets, deployment |
| Agent class | Agents API | Agent lifecycle, patterns, pitfalls |
| State | Store and sync state | setState, validateStateChange, persistence |
| Routing | Routing | URL patterns, routeAgentRequest |
| Callable methods | Callable methods | @callable, RPC, streaming, timeouts |
| Scheduling | Schedule tasks | schedule(), scheduleEvery(), cron |
| Workflows | Run workflows | AgentWorkflow, durable multi-step tasks |
| HTTP/WebSockets | WebSockets | Lifecycle hooks, hibernation |
| Chat agents | Chat agents | AIChatAgent, streaming, tools, persistence |
| Client SDK | Client SDK | useAgent, AgentClient, state, RPC, HTTP |
| Client tools | Client tools | Client-side tools, autoContinueAfterToolResult |
| Server-driven messages | Autonomous responses | saveMessages, waitUntilStable, server-initiated turns |
| Resumable streaming | Chat agents | Stream recovery on disconnect |
| Email routing, secure reply resolver | ||
| MCP client | MCP client | Connecting to MCP servers |
| MCP server | MCP server | Building MCP servers with createMcpHandler |
| MCP transports | MCP transports | Streamable HTTP, SSE, RPC transport options |
| Securing MCP servers | Securing MCP | OAuth, proxy MCP, hardening |
| Human-in-the-loop | Human-in-the-loop | Workflow approvals, elicitation, timeout handling |
| Durable execution | Durable execution | runFiber(), stash(), surviving DO eviction |
| Queue | Queue | Built-in FIFO queue, queue() |
| Retries | Retries | this.retry(), backoff/jitter |
| Observability | Observability | Diagnostics-channel events |
| Push notifications | Push notifications | Web Push + VAPID from agents |
| Webhooks | Webhooks | Receiving external webhooks |
| Cross-domain auth | Cross-domain auth | WebSocket auth, tokens, CORS |
| Readonly connections | Readonly | shouldConnectionBeReadonly |
| Voice | Voice | Experimental STT/TTS, withVoice |
| Browse the web | Browser tools | Experimental CDP browser automation |
| Think | Think | Experimental higher-level chat agent class |
| Migrations | AI SDK v5, AI SDK v6 | Upgrading @cloudflare/ai-chat |
Capabilities
The Agents SDK provides:
- Persistent state โ SQLite-backed, auto-synced to clients via
setState - Callable RPC โ
@callable()methods invoked over WebSocket - Scheduling โ One-time, recurring (
scheduleEvery), and cron tasks - Workflows โ Durable multi-step background processing via
AgentWorkflow - Durable execution โ
runFiber()/stash()for work that survives DO eviction - Queue โ Built-in FIFO queue with retries via
queue() - Retries โ
this.retry()with exponential backoff and jitter - MCP integration โ Connect to MCP servers or build your own with
createMcpHandler - Email handling โ Receive and reply to emails with secure routing
- Streaming chat โ
AIChatAgentwith resumable streams, message persistence, tools - Server-driven messages โ
saveMessages,waitUntilStablefor proactive agent turns - React hooks โ
useAgent,useAgentChatfor client apps - Observability โ
diagnostics_channelevents for state, RPC, schedule, lifecycle - Push notifications โ Web Push + VAPID delivery from agents
- Webhooks โ Receive and verify external webhooks
- Voice (experimental) โ STT/TTS via
@cloudflare/voice - Browser tools (experimental) โ CDP-powered browsing via
agents/browser - Think (experimental) โ Higher-level chat agent via
@cloudflare/think
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}:
| Class | URL |
|---|---|
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
| Task | API |
|---|---|
| Read state | this.state.count |
| Write state | this.setState({ count: 1 }) |
| SQL query | this.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 workflow | await this.runWorkflow("ProcessingWorkflow", params) |
| Durable fiber | await this.runFiber("name", async (ctx) => { ... }) |
| Enqueue work | this.queue("handler", payload) |
| Retry with backoff | await this.retry(fn, { maxAttempts: 5 }) |
| Broadcast to clients | this.broadcast(message) |
| Get connections | this.getConnections(tag?) |
React Client
Read client-sdk.md for client selection and current connection examples. For chat UI and tools, also read streaming-chat.md.
References
Core
- references/state-scheduling.md โ State persistence, scheduling, SQL
- references/callable.md โ RPC methods, streaming, timeouts
- references/routing.md โ URL patterns, custom routing,
getAgentByName - references/configuration.md โ Wrangler config, bindings, Vite setup
Chat & Streaming
- references/streaming-chat.md โ AIChatAgent, resumable streams, tools
- references/client-sdk.md โ
useAgent,useAgentChat,AgentClient - references/server-driven-messages.md โ Trigger patterns,
saveMessages - references/human-in-the-loop.md โ Approval flows,
needsApproval
Background Processing
- references/workflows.md โ Durable Workflows integration
- references/durable-execution.md โ
runFiber,stash, surviving eviction - references/queue-retries.md โ Built-in queue, retry with backoff
Integrations
- references/mcp.md โ MCP client and server, transports, securing
- references/email.md โ Email routing and handling
- references/webhooks-push.md โ Webhooks, push notifications
- references/observability.md โ Diagnostics-channel events
Experimental
- references/think.md โ
@cloudflare/thinkhigher-level chat agent - references/voice.md โ
@cloudflare/voiceSTT/TTS - references/codemode.md โ Code Mode for tool orchestration
- references/browse-the-web.md โ CDP browser tools
npx skills add cloudflare/skills --skill "agents-sdk" --full-depthRun this in your project โ your agent picks the skill up automatically.
FIRST: Verify Installation
npm ls agents # Should show agents packageIf not installed:
npm install agentsFor chat agents:
npm install agents @cloudflare/ai-chat ai @ai-sdk/reactWrangler Configuration
{
"compatibility_flags": ["nodejs_compat"],
"durable_objects": {
"bindings": [{ "name": "MyAgent", "class_name": "MyAgent" }]
},
"migrations": [{ "tag": "v1", "new_sqlite_classes": ["MyAgent"] }]
}Gotchas:
- Do NOT enable
experimentalDecoratorsin tsconfig (breaks@callable) - Never edit old migrations โ always add new tags
- Each agent class needs its own DO binding + migration entry
- Add
"ai": { "binding": "AI" }for Workers AI
No common issues documented yet. If you hit a problem, the repository's GitHub Issues page is the best place to look.
Licensed under Apache-2.0โ you can use, modify, and redistribute it under that license's terms.
View the full license file on GitHub โ