← 返回 Skills 市场
creativerezz

Agents Sdk

作者 Reza · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
21
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install agents-sdk
功能描述
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks,...
使用说明 (SKILL.md)

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Your knowledge of the Agents SDK may be outdated.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\x3CEnv, State> {
  initialState = { count: 0 };

  validateStateChange(nextState: State, source: Connection | "server") {
    if (nextState.count \x3C 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 (
    \x3Cbutton onClick={() => agent.setState({ count: state.count + 1 })}>
      Count: {state.count}
    \x3C/button>
  );
}

References

Core

Chat & Streaming

Background Processing

Integrations

Experimental

安全使用建议
Install only if you are building Cloudflare Agents SDK projects. Treat examples as starting points: avoid long-lived tokens in URLs, verify webhooks using a single buffered raw body, connect only trusted MCP servers, filter model-accessible tools, and restrict browser automation to authorized domains and non-sensitive sessions.
能力标签
requires-walletrequires-oauth-tokenrequires-sensitive-credentials
能力评估
Purpose & Capability
The artifacts coherently document Cloudflare Agents SDK features: persistent state, workflows, WebSockets, MCP, chat, voice, browser automation, webhooks, email, and push notifications.
Instruction Scope
The skill trigger is broad and some examples expose powerful patterns, but I found no hidden role changes, prompt override attempts, or unrelated instructions.
Install Mechanism
The package contains markdown documentation only; npm commands are user-facing setup examples, with no executable scripts, install hooks, or bundled runtime payload.
Credentials
Use of Cloudflare bindings, secrets, OAuth-like tokens, browser tools, and MCP servers is proportionate to the SDK purpose, though users should scope and review these integrations carefully.
Persistence & Privilege
The docs intentionally cover durable state, schedules, queues, workflows, message persistence, browser code execution, and MCP tools; the skill itself does not create persistence or elevate privileges on install.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install agents-sdk
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /agents-sdk 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of agents-sdk. - Launches Cloudflare Agents SDK for building AI agents on Cloudflare Workers. - Provides comprehensive documentation covering persistent state, workflows, WebSockets, scheduling, queues, retries, observability, chat, voice, and browser automation. - Includes a detailed table linking every core and advanced SDK capability to Cloudflare documentation for easy reference. - Emphasizes use of up-to-date docs over pre-trained knowledge for all Agents SDK tasks. - Features installation and configuration guides, example code, and a list of common pitfalls.
元数据
Slug agents-sdk
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Agents Sdk 是什么?

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 21 次。

如何安装 Agents Sdk?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install agents-sdk」即可一键安装,无需额外配置。

Agents Sdk 是免费的吗?

是的,Agents Sdk 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Agents Sdk 支持哪些平台?

Agents Sdk 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Agents Sdk?

由 Reza(@creativerezz)开发并维护,当前版本 v1.0.0。

💬 留言讨论