Verified project record

openai/openai-agents-python

A Python framework for building multi-agent workflows, supporting orchestration, tools, guardrails, and handoffs across 100+ language models. It requires a Python environment and external API configuration to operate.

Project overview

Project type: AI Agent · Workflow
Use cases: Coding & Development · Automation
Deployment: Refer to project documentation
License: MIT

Best for

Developers and AI engineers who need to build multi-agent workflows in Python and require provider-agnostic LLM support.
Teams needing built-in mechanisms for human-in-the-loop interventions, session management, and agent tracing.

Key capabilities

Enables building multi-agent workflows with agents configured with instructions, tools, guardrails, and handoffs.
Delegating to other agents for specific tasks.
Various tools let agents take actions including functions, MCP, and hosted tools.
Configurable safety checks for input and output validation.
Built-in mechanisms for involving humans across agent runs.
Automatic conversation history management across agent runs.
Built-in tracking of agent runs, allowing you to view, debug and optimize your workflows.
Agents preconfigured to work with a container to inspect files, run commands, apply patches, or preserve workspace state.

Limitations and risks

Python 3.10 or newer is required to use the framework.
UnixLocalSandboxClient is supported only on macOS and Linux; Windows requires DockerSandboxClient.

Getting started

Create and activate a Python virtual environment (3.10+), install the package via pip or uv, set the OPENAI_API_KEY, and run a text agent example.

Evidence and sources

README: 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 API…
GitHub project description: A lightweight, powerful framework for multi-agent workflows
README: **[Agents as tools](https://openai.github.io/openai-agents-python/tools/#agents-as-tools) / [Handoffs](https://openai.github.io/openai-agents-python/handoffs/)**: Delegating to ot…
README: [**Tools**](https://openai.github.io/openai-agents-python/tools/): Various Tools let agents take actions (functions, MCP, hosted tools)
README: [**Guardrails**](https://openai.github.io/openai-agents-python/guardrails/): Configurable safety checks for input and output validation

Reviewed at: 2026-07-17T13:22:59Z