Built-in agent loop
Handles tool invocation, returns tool results to the language model, and continues execution until the task is complete. TypeScript functions can become tools with automatic schema generation and schema-based validation.
A TypeScript SDK for developers building text, sandbox, and realtime voice agents.
OpenAI Agents SDK TypeScript is a developer toolkit for building agentic AI applications with a small set of primitives. Agents combine language models with instructions and tools, while native TypeScript supports orchestration without requiring a separate workflow language.
The SDK supports text tasks, agents that work in isolated filesystem workspaces, and realtime spoken interactions. It brings execution, delegation, validation, and tracing into one toolkit, with OpenAI model support included by default and an adapter for supported Vercel AI SDK models.
Handles tool invocation, returns tool results to the language model, and continues execution until the task is complete. TypeScript functions can become tools with automatic schema generation and schema-based validation.
Provides isolated filesystems, shell commands, file editing, snapshots, and sandbox session state for tasks that need a persistent working environment.
Supports low-latency spoken interactions with automatic interruption detection and context management. In browsers, RealtimeSession can connect microphone input and audio output through WebRTC.
Coordinates specialized agents through agents as tools and handoffs. Built-in MCP integration exposes server tools alongside local function tools.
Runs input guardrails in parallel with agent execution and fails fast when checks do not pass. Human-in-the-loop mechanisms allow people to participate across agent runs.
Built-in tracing visualizes, debugs, and monitors agent workflows. Sessions maintain working context within an agent loop, while tracing supports OpenAI evaluation, fine-tuning, and distillation tools.
Give a workspace assistant a Git repository to inspect, summarize, or modify using sandbox files and shell commands. Snapshots and session state support work that spans longer tasks.
Build an assistant that accepts microphone input and responds with audio while using tools and preserving conversation history. Interruption handling supports back-and-forth spoken exchanges.
Route parts of a larger task to agents with different instructions and tools, using handoffs or agent-as-tool calls to coordinate their contributions.
Run `npm install @openai/agents zod`. The SDK requires Zod v4. For the documented OpenAI text and sandbox examples, set the OPENAI_API_KEY environment variable.
Use @openai/agents for most text, sandbox, and realtime applications. Choose @openai/agents-realtime when you only need the standalone realtime package. Lower-level packages support custom provider wiring and specific integrations.
Yes, through the Vercel AI SDK adapter in @openai/agents-extensions. It supports AI SDK provider specification versions v2, v3, and v4. The adapter is in beta; the documentation recommends testing your chosen provider and using the default provider for OpenAI models.
It does not support deferred Responses tool loading, tool search, or Programmatic Tool Calling. PDF inputs can use base64 data or public URLs, subject to provider support; OpenAI file IDs are not supported through the adapter.
トラフィックデータは参考情報としてご利用ください。
| 6月 | 114444 |
|---|---|
| 7月 | 133472 |
| 8月 | 148025 |
トラフィック分析データはまだありません。
agents.cloudflare.com
A platform and SDK for developers building AI agents with persistent state and tools.
adk.dev
Agent Development Kit (ADK) is an open-source framework for building, evaluating, and deploying conversational and non-conversational AI agents. It supports multi-agent systems, tools, structured workflows, and production runtimes across Python, TypeScript, Go, Java, and Kotlin.
vapi.ai
A developer platform for building, testing, and operating conversational voice AI agents.

soundhound.com
A voice-native platform for building, testing, and operating AI agents for customer and employee interactions.
www.stagehand.dev
Stagehand is an SDK for building browser agents with Playwright-style APIs, natural-language actions, structured extraction, and self-healing behavior. It supports TypeScript, Python, and Go for agents that need to operate web pages with browser-level control.
aistudio.google.com
Google AI Studio is a browser-based development environment for experimenting with Google’s generative models and moving prompts into applications through the Gemini API. It supports developers building text, image, video, audio, and agent experiences.