Glossary · Agentic AI
What is OpenAI Agents SDK? Definition and meaning
A lightweight SDK with agents, handoffs, guardrails and tracing for multi-agent applications.
Definition
OpenAI Agents SDK: A lightweight SDK with agents, handoffs, guardrails and tracing for multi-agent applications.
In short: OpenAI's SDK for agent workflows.
When it is used
Orchestrating tool-using agents on OpenAI models.
Where it fits
OpenAI Agents SDK belongs to Agent SDKs in the Agentic AI topic. These are the other terms in the same group:
- Claude Agent SDK: A Python and TypeScript SDK that exposes the same agent loop, tools and context management that power Claude Code.
- Google ADK: An open-source framework for building, evaluating and deploying agents, with support for multi-agent designs and Gemini.
- Microsoft Agent Framework: A framework for building single and multi-agent applications in Python and .NET, generally available since April 2026.
Learn more
The full guide to OpenAI Agents SDK explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: ONNX Runtime · Next term: OpenCV