openai-agents-python

A lightweight, powerful framework for multi-agent workflows

What is openai-agents-python?

A lightweight, powerful framework for multi-agent workflows

Overview of openai-agents-python

What it is

The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows. It is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs, as well as 100+ other LLMs. The SDK includes core concepts such as Agents, Sandbox agents, Realtime agents, Voice agents, Agents as tools/Handoffs, Tools, Guardrails, Human in the loop, Sessions, and Tracing.

Key features

  • Agents: LLMs configured with instructions, tools, guardrails, and handoffs.
  • Sandbox agents: Preconfigured agents that work with a container for long time horizon tasks.
  • Realtime agents: Build voice agents with gpt-realtime-2.1 and full agent features.
  • Voice agents: Voice pipelines combining speech-to-text, agent workflow, and text-to-speech.
  • Handoffs: Delegating to other agents for specific tasks.
  • Tools: Various tools (functions, MCP, hosted tools) for agents to take actions.
  • Guardrails: Configurable safety checks for input and output validation.
  • Human in the loop: Built-in mechanisms for involving humans across agent runs.
  • Sessions: Automatic conversation history management across agent runs.
  • Tracing: Built-in tracking of agent runs for viewing, debugging, and optimizing workflows.

Use cases

  • Building multi-agent workflows that require coordination between multiple LLM-powered agents.
  • Creating sandboxed environments for agents to inspect files, run commands, apply patches, or preserve workspace state over long tasks.
  • Developing low-latency voice and multimodal experiences using realtime agents over WebSocket.
  • Implementing voice pipelines that convert audio to text, run an agent workflow, and stream generated speech.
  • Delegating specific tasks to specialized agents via handoffs.

Getting started

Set up a Python environment (Python 3.10 or newer) and install the package. bash python -m venv .venv source .venv/bin/activate # On Windows: .venv/Scripts/activate pip install openai-agents For voice support: pip install 'openai-agents[voice]'. For Redis session support: pip install 'openai-agents[redis]'. Alternatively, using uv: bash uv init uv add openai-agents For voice support: uv add 'openai-agents[voice]'. For Redis session support: uv add 'openai-agents[redis]'. Set the OPENAI_API_KEY environment variable before running examples.

License and pricing

The project is licensed under the MIT License and is open source. No pricing information is stated.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/openaiopenai-agents-python.svg)](https://yunodb.com/tools/openaiopenai-agents-python?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/openaiopenai-agents-python?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/openaiopenai-agents-python.svg" alt="Featured on YunoDB" height="20"></a>