agents-sdk

oleh openai

Bangun, jalankan, sebarkan, dan evaluasi aplikasi OpenAI Agents SDK dari Codex. Gunakan saat pengguna meminta untuk membuat atau menyesuaikan aplikasi Agents SDK, membangun dari perintah atau Codex…

npx skills add https://github.com/openai/plugins --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Your knowledge of the Agents SDK may be outdated.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

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

TopicDocUse for
Getting starteddocs/getting-started.mdFirst agent, project setup
Statedocs/state.mdsetState, validateStateChange, persistence
Routingdocs/routing.mdURL patterns, routeAgentRequest, basePath
Callable methodsdocs/callable-methods.md@callable, RPC, streaming, timeouts
Schedulingdocs/scheduling.mdschedule(), scheduleEvery(), cron
Workflowsdocs/workflows.mdAgentWorkflow, durable multi-step tasks
HTTP/WebSocketsdocs/http-websockets.mdLifecycle hooks, hibernation
Emaildocs/email.mdEmail routing, secure reply resolver
MCP clientdocs/mcp-client.mdConnecting to MCP servers
MCP serverdocs/mcp-servers.mdBuilding MCP servers with McpAgent
Client SDKdocs/client-sdk.mduseAgent, useAgentChat, React hooks
Human-in-the-loopdocs/human-in-the-loop.mdApproval flows, pausing workflows
Resumable streamingdocs/resumable-streaming.mdStream 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

npm ls agents  # Should show agents package

If not installed:

npm install agents

Wrangler Configuration

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

Agent Class

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}:

ClassURL
Counter/agents/counter/user-123
ChatRoom/agents/chat-room/lobby

Client: useAgent({ agent: "Counter", name: "user-123" })

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)

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

Lebih banyak skill dari openai

user-context
openai
Memuat atau mengelola preferensi perutean sumber daya tahan lama, logika orientasi, kemajuan pengaturan, dan registri lapisan semantik dari plugin Data Analytics.
official
notion-research-documentation
openai
Teliti konten Notion dan sintesis menjadi ringkasan terstruktur, laporan, atau perbandingan dengan kutipan. Cari dan ambil halaman Notion menggunakan kueri yang ditargetkan, lalu atur temuan berdasarkan tema dengan kutipan sumber sebaris dan bagian referensi. Pilih dari empat format keluaran (ringkasan cepat, ringkasan riset, perbandingan, laporan komprehensif) berdasarkan cakupan dan tujuan pengguna. Buat dan perbarui halaman Notion menggunakan templat bawaan; tautkan sumber secara langsung dan lacak perubahan saat informasi baru tiba...
official
rcsb-pdb-skill
openai
Kirim permintaan RCSB PDB yang ringkas untuk metadata inti, kueri API Pencarian, dan unduhan FASTA. Gunakan saat pengguna menginginkan ringkasan RCSB yang singkat; simpan JSON mentah atau…
official
pdf
openai
Pembacaan, pembuatan, dan validasi PDF dengan rendering visual dan pembuatan secara terprogram. Render halaman PDF ke PNG untuk inspeksi visual tata letak, spasi, dan tipografi sebelum pengiriman menggunakan Poppler (pdftoppm). Buat PDF secara terprogram dengan reportlab untuk pemformatan yang andal; ekstrak teks dan metadata dengan pdfplumber atau pypdf. Terapkan standar kualitas: tidak ada teks terpotong, elemen tumpang tindih, tabel rusak, atau artefak rendering; hanya tanda hubung ASCII, kutipan yang dapat dibaca manusia. Gunakan...
official
test-coverage-improver
openai
Improve test coverage in the OpenAI Agents JS monorepo: run `pnpm test:coverage`, inspect coverage artifacts, identify low-coverage files and branches, propose…
official
playwright
openai
Otomasi peramban berbasis terminal dengan snapshot elemen dan alur kerja UI interaktif. Beroperasi melalui skrip wrapper playwright-cli (memerlukan npx); mendukung mode headless dan headed untuk debugging visual. Alur kerja inti: buka halaman, ambil snapshot untuk referensi elemen stabil, berinteraksi menggunakan ref, ambil snapshot ulang setelah navigasi atau perubahan DOM. Termasuk pengisian formulir, klik, pengetikan, manajemen multi-tab, tangkapan layar/PDF, dan perekaman jejak untuk debugging alur. Referensi elemen (misalnya e3, e15)...
official
ukb-topmed-phewas-skill
openai
Ambil ringkasan PheWAS UKB-TOPMed yang ringkas untuk varian tunggal dengan menerima masukan rsID, GRCh37, atau GRCh38 dan menyelesaikannya ke kueri GRCh38 yang diperlukan. Gunakan ketika...
official
code-review-context
openai
Konteks yang terlihat oleh model
official