Catalog
cloudflare/agents-sdk

cloudflare

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, 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.

global
New~3.0k
v1.0Saved Jul 11, 2026

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Your knowledge of the Agents SDK may be outdated.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, useAgentChat, React hooks
Client tools Client tools Client-side tools, autoContinueAfterToolResult
Server-driven messages Trigger patterns saveMessages, waitUntilStable, server-initiated turns
Resumable streaming Resumable streaming Stream recovery on disconnect
Email Email Email routing, secure reply resolver
MCP client MCP client Connecting to MCP servers
MCP server MCP server Building MCP servers with McpAgent
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 Approval flows, needsApproval, workflows
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 — 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}:

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

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

Files20
20 files · 59.7 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Safety

82

Quality

85

Clarity

88

Completeness

76

Summary

The Cloudflare Agents SDK skill provides comprehensive guidance on building AI agents on Cloudflare Workers with state management, scheduling, workflows, MCP integration, and experimental features. The skill is documentation-heavy, primarily instructing agents to retrieve details from Cloudflare's official docs rather than relying on pre-trained knowledge. Scope is very broad—covering 19+ reference files across core APIs, integrations, and experimental features—but boundaries are explicit and well-documented through topic-specific reference files.

Static Analysis Findings

1 finding

Patterns detected by deterministic static analysis before AI scoring. Hover over any finding code for detailed information and remediation guidance.

Credential Exposure
SEC-020Direct .env File Access12x in 8 files

Direct .env file access

references/browse-the-web.md.env3x
references/email.md.env
references/codemode.md.env

Detected Capabilities

documentation retrievalcode example generationconfiguration guidanceAPI referenceagent class scaffoldingTypeScript type definitions

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

build cloudflare agentsagents sdk setupdurable state managementagent scheduling tasksstreaming chat agentsmcp integration agentsworker state persistenceagent workflows

Risk Signals

INFO

SEC-020: Direct .env file access mentioned in multiple reference files

references/browse-the-web.md, references/email.md, references/codemode.md, references/streaming-chat.md, references/mcp.md, references/voice.md, references/webhooks-push.md, references/think.md
INFO

References to external MCP servers and OAuth flows

references/mcp.md
INFO

Email signature verification and secure reply resolvers mentioned

references/email.md
INFO

VAPID key generation and storage referenced

references/webhooks-push.md

Referenced Domains

External domains referenced in skill content, detected by static analysis.

api.example.comdevelopers.cloudflare.comexample.commy-worker.workers.devwww.apache.org

Use Cases

  • Build stateful agents on Cloudflare Workers
  • Implement persistent agent state and scheduling
  • Create chat agents with streaming and tools
  • Integrate MCP servers and clients
  • Set up email routing and webhook handling
  • Deploy voice agents and browser automation
  • Build workflows with human approval loops
  • Configure durable execution and retries

Quality Notes

  • Strength: Comprehensive reference material with clear topic hierarchy and links to official Cloudflare docs at every section
  • Strength: Well-organized reference files with TypeScript examples, API tables, and usage patterns
  • Strength: Clear scope boundaries — each reference file focuses on a specific capability (state, scheduling, MCP, email, etc.)
  • Strength: Explicit 'Fetch from docs' instruction at top establishes bias toward retrieval over pre-training
  • Strength: Error handling patterns documented (e.g., signature verification, retry strategies)
  • Limitation: .env references are educational (showing how to use secrets) rather than instructing the agent to read them unsupervised
  • Limitation: Experimental features (Think, Voice, Browse, Codemode) are marked as such with appropriate caveats
  • Limitation: No dedicated 'gotchas' or 'common mistakes' sections beyond brief notes — could expand error guidance
Model: claude-haiku-4-5-20251001Analyzed: Jul 11, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Add cloudflare/agents-sdk to your library

Command Palette

Search for a command to run...

cloudflare/agents-sdk | SkillRepo