About OpenAI Agents SDK
The OpenAI Agents SDK is an open source Python library for building agent apps. It keeps the set of core ideas small: agents, handoffs, guardrails and tracing.
What it does
You create agents with instructions and tools, and the SDK runs the loop until the task finishes. One agent can hand work to another, and guardrails can check inputs and outputs. Built-in tracing records each run so you can review what happened.
Key features
- Agents with instructions and tools
- Handoffs between agents
- Input and output guardrails
- Built-in tracing of runs
- Voice and realtime agent options
Who it's for
Python developers who want a small, readable framework for agent workflows, especially those already using OpenAI models. It is also a practical option for quick prototypes.
Pricing and good to know
The SDK is open source under the MIT license and free to install. Model usage is billed through the model provider you use. Check the documentation for which features each model supports before you design around them.
Highlights
- Agents with instructions and tools
- Handoffs between agents
- Input and output guardrails
- Built-in tracing of runs
- Voice and realtime agent options
