# OpenAI Agents SDK — Build Multi-Agent Systems in Python

> Official OpenAI Python SDK for building multi-agent systems with handoffs, guardrails, and tracing. Agents delegate to specialists, enforce safety rules, and produce observable traces. 8,000+ stars.

## Install

Save as a script file and run:

## Quick Use

```bash
pip install openai-agents
```

```python
from agents import Agent, Runner

agent = Agent(
    name="assistant",
    instructions="You are a helpful assistant.",
    model="gpt-4o",
)

result = Runner.run_sync(agent, "What is the capital of France?")
print(result.final_output)
```

---

## Intro

OpenAI Agents SDK is the official Python framework for building multi-agent systems with handoffs, guardrails, and tracing with 8,000+ GitHub stars. Define agents with instructions and tools, set up handoff rules for delegation between specialists, add guardrails for input/output safety, and get full execution traces for debugging. Unlike generic agent frameworks, this SDK is designed specifically for OpenAI models with first-class support for their function calling and structured output APIs. Best for developers building production agent systems on OpenAI models. Works with: GPT-4o, o3, any OpenAI model. Setup time: under 2 minutes.

---

## Core Concepts

### Agents with Tools

```python
from agents import Agent, function_tool

@function_tool
def get_weather(city: str) -> str:
    'Get weather for a city.'
    return f"Weather in {city}: 22C, sunny"

agent = Agent(
    name="weather-bot",
    instructions="You help users check the weather.",
    tools=[get_weather],
)
```

### Handoffs (Agent Delegation)

```python
billing_agent = Agent(
    name="billing",
    instructions="Handle billing questions. Access to payment tools.",
    tools=[get_invoice, process_refund],
)

support_agent = Agent(
    name="support",
    instructions="Handle general support. Hand off billing questions to billing agent.",
    handoffs=[billing_agent],
)

# When user asks about billing, support_agent hands off to billing_agent
```

### Guardrails

```python
from agents import GuardrailFunctionOutput, input_guardrail

@input_guardrail
async def block_harmful(ctx, agent, input_text):
    if "hack" in input_text.lower():
        return GuardrailFunctionOutput(
            output_info={"reason": "Potentially harmful request"},
            tripwire_triggered=True,
        )

agent = Agent(
    name="safe-agent",
    input_guardrails=[block_harmful],
)
```

### Tracing
Every agent run produces a detailed trace:

```python
result = Runner.run_sync(agent, "Help me with my order")
# View trace at: https://platform.openai.com/traces/{trace_id}
# Shows: agent decisions, tool calls, handoffs, guardrail checks
```

### Structured Output

```python
from pydantic import BaseModel

class OrderSummary(BaseModel):
    order_id: str
    status: str
    total: float

agent = Agent(
    name="order-agent",
    output_type=OrderSummary,  # Enforces structured response
)
```

### Multi-Agent Architecture

```python
researcher = Agent(name="researcher", tools=[search_web])
writer = Agent(name="writer", handoffs=[researcher])
editor = Agent(name="editor", handoffs=[writer])

# editor -> writer -> researcher (chain of delegation)
result = Runner.run_sync(editor, "Write an article about AI agents")
```

### Key Stats
- 8,000+ GitHub stars
- Official OpenAI product
- Handoffs for agent delegation
- Input/output guardrails
- Built-in tracing and observability

### FAQ

**Q: What is OpenAI Agents SDK?**
A: The official Python SDK for building multi-agent systems with handoffs between specialists, safety guardrails, and execution tracing.

**Q: Is it free?**
A: The SDK is open-source under MIT. You need an OpenAI API key.

**Q: Does it work with Claude or other models?**
A: Designed for OpenAI models. For multi-model support, use LangGraph or CrewAI instead.

---

## Source & Thanks

> Created by [OpenAI](https://github.com/openai). Licensed under MIT.
>
> [openai-agents-python](https://github.com/openai/openai-agents-python) — stars 8,000+

Thanks to OpenAI for standardizing multi-agent patterns.

---

<!-- ZH -->

## 快速使用

```bash
pip install openai-agents
```

```python
from agents import Agent, Runner
agent = Agent(name="assistant", instructions="你是一个有用的助手。")
result = Runner.run_sync(agent, "法国的首都是什么?")
```

---

## 简介

OpenAI Agents SDK 是 OpenAI 官方 Python 多 Agent 框架，GitHub 8,000+ stars。支持 Agent 间委派（Handoffs）、安全护栏（Guardrails）和执行追踪（Tracing）。适合在 OpenAI 模型上构建生产 Agent 系统。

---

## 来源与感谢

> Created by [OpenAI](https://github.com/openai). Licensed under MIT.
>
> [openai-agents-python](https://github.com/openai/openai-agents-python) — stars 8,000+

---
Source: https://tokrepo.com/en/workflows/38035d0b-f942-4bf2-bbad-be9d4f719c00
Author: Agent Toolkit