OpenAI Agents SDK

What it does

A lightweight Python framework for building agents and multi-agent workflows. It covers agents with tools and handoffs, guardrails, human-in-the-loop, sessions, tracing, sandbox agents and voice/realtime agents. It works with OpenAI's APIs and, per the README, 100+ other LLMs. A JS/TS version exists too. MIT licensed.

Who it's for

Python developers building their own agents who want a small, well-documented framework.

How to set it up

1. Needs Python 3.10 or newer. Install:

   bashCopy

   python -m venv .venv
   source .venv/bin/activate
   pip install openai-agents

2. Or with uv:

   bashCopy

   uv init
   uv add openai-agents

3. Set OPENAI_API_KEY and run a first agent:

   textCopy

   from agents import Agent, Runner
   
   agent = Agent(name="Assistant", instructions="You are a helpful assistant")
   result = Runner.run_sync(agent, "Write a haiku about recursion in programming.")
   print(result.final_output)

Check the official OpenAI Agents SDK docs for the latest steps.

Example prompts

Build a triage agent with the OpenAI Agents SDK that hands off to a billing agent or a support agent.

Add an input guardrail that blocks requests unrelated to our product.

Connect my agent to a local MCP server and list the tools it can see.

Demo