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, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

685 stars

Best use case

agents-sdk is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Teams using agents-sdk should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/agents-sdk/SKILL.md --create-dirs "https://raw.githubusercontent.com/openai/plugins/main/plugins/cloudflare/skills/agents-sdk/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/agents-sdk/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How agents-sdk Compares

Feature / Agentagents-sdkStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Cloudflare Agents SDK

Your knowledge of the Agents SDK may be outdated.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

## Retrieval Sources

Fetch current docs from `https://github.com/cloudflare/agents/tree/main/docs` before implementing.

| Topic | Doc | Use for |
|-------|-----|---------|
| Getting started | `docs/getting-started.md` | First agent, project setup |
| State | `docs/state.md` | `setState`, `validateStateChange`, persistence |
| Routing | `docs/routing.md` | URL patterns, `routeAgentRequest`, `basePath` |
| Callable methods | `docs/callable-methods.md` | `@callable`, RPC, streaming, timeouts |
| Scheduling | `docs/scheduling.md` | `schedule()`, `scheduleEvery()`, cron |
| Workflows | `docs/workflows.md` | `AgentWorkflow`, durable multi-step tasks |
| HTTP/WebSockets | `docs/http-websockets.md` | Lifecycle hooks, hibernation |
| Email | `docs/email.md` | Email routing, secure reply resolver |
| MCP client | `docs/mcp-client.md` | Connecting to MCP servers |
| MCP server | `docs/mcp-servers.md` | Building MCP servers with `McpAgent` |
| Client SDK | `docs/client-sdk.md` | `useAgent`, `useAgentChat`, React hooks |
| Human-in-the-loop | `docs/human-in-the-loop.md` | Approval flows, pausing workflows |
| Resumable streaming | `docs/resumable-streaming.md` | Stream recovery on disconnect |

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

## Capabilities

The Agents SDK provides:

- **Persistent state** - SQLite-backed, auto-synced to clients
- **Callable RPC** - `@callable()` methods invoked over WebSocket
- **Scheduling** - One-time, recurring (`scheduleEvery`), and cron tasks
- **Workflows** - Durable multi-step background processing via `AgentWorkflow`
- **MCP integration** - Connect to MCP servers or build your own with `McpAgent`
- **Email handling** - Receive and reply to emails with secure routing
- **Streaming chat** - `AIChatAgent` with resumable streams
- **React hooks** - `useAgent`, `useAgentChat` for client apps

## FIRST: Verify Installation

```bash
npm ls agents  # Should show agents package
```

If not installed:
```bash
npm install agents
```

## Wrangler Configuration

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

## Agent Class

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

type State = { count: number };

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

  // Validation hook - runs before state persists (sync, throwing rejects the update)
  validateStateChange(nextState: State, source: Connection | "server") {
    if (nextState.count < 0) throw new Error("Count cannot be negative");
  }

  // Notification hook - runs after state persists (async, non-blocking)
  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" })`

## 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)` |

## React Client

```tsx
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

- **[references/workflows.md](references/workflows.md)** - Durable Workflows integration
- **[references/callable.md](references/callable.md)** - RPC methods, streaming, timeouts
- **[references/state-scheduling.md](references/state-scheduling.md)** - State persistence, scheduling
- **[references/streaming-chat.md](references/streaming-chat.md)** - AIChatAgent, resumable streams
- **[references/mcp.md](references/mcp.md)** - MCP server integration
- **[references/email.md](references/email.md)** - Email routing and handling
- **[references/codemode.md](references/codemode.md)** - Code Mode (experimental)

Related Skills

workflow

685
from openai/plugins

Vercel Workflow DevKit (WDK) expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.

verification

685
from openai/plugins

Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.

vercel-storage

685
from openai/plugins

Vercel storage expert guidance — Blob, Edge Config, and Marketplace storage (Neon Postgres, Upstash Redis). Use when choosing, configuring, or using data storage with Vercel applications.

vercel-services

685
from openai/plugins

Vercel Services — deploy multiple services within a single Vercel project. Use for monorepo layouts or when combining a backend (Python, Go) with a frontend (Next.js, Vite) in one deployment.

vercel-sandbox

685
from openai/plugins

Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.

vercel-queues

685
from openai/plugins

Vercel Queues guidance (public beta) — durable event streaming with topics, consumer groups, retries, and delayed delivery. $0.60/1M ops. Powers Workflow DevKit. Use when building async processing, fan-out patterns, or event-driven architectures.

vercel-functions

685
from openai/plugins

Vercel Functions expert guidance — Serverless Functions, Edge Functions, Fluid Compute, streaming, Cron Jobs, and runtime configuration. Use when configuring, debugging, or optimizing server-side code running on Vercel.

vercel-flags

685
from openai/plugins

Vercel Flags guidance — feature flags platform with unified dashboard, Flags Explorer, gradual rollouts, A/B testing, and provider adapters. Use when implementing feature flags, experimentation, or staged rollouts.

vercel-firewall

685
from openai/plugins

Vercel Firewall and security expert guidance. Use when configuring DDoS protection, WAF rules, rate limiting, bot filtering, IP allow/block lists, OWASP rulesets, Attack Challenge Mode, or any security configuration on the Vercel platform.

vercel-cli

685
from openai/plugins

Vercel CLI expert guidance. Use when deploying, managing environment variables, linking projects, viewing logs, managing domains, or interacting with the Vercel platform from the command line.

vercel-api

685
from openai/plugins

Vercel MCP and REST API expert guidance. Use when the agent needs live access to Vercel projects, deployments, environment variables, domains, logs, or documentation through the MCP server or REST API.

vercel-agent

685
from openai/plugins

Vercel Agent guidance — AI-powered code review, incident investigation, and SDK installation. Automates PR analysis and anomaly debugging. Use when configuring or understanding Vercel's AI development tools.