← Back to all projects

OpenAI Agents SDK

A deliberately small agent framework from OpenAI

OfficialMIT
Stars
30.4k
Forks
5k
Open issues
19
Last commit
30 Oct 2026

What is OpenAI Agents SDK?

Few primitives — agents, handoffs, guardrails, tracing — and little else. The small surface area is the appeal: there is not much to learn and not much to fight. It is built around OpenAI's own models first, so weigh that if multi-provider portability matters to you.

What can you do with OpenAI Agents SDK?

  • Delegate between specialist agents — Handoffs and agents-as-tools let one Agent pass work to another, and Runner.run_sync executes the whole chain and returns final_output.
  • Give an agent a workspace — SandboxAgent takes a Manifest of entries such as GitRepo and runs commands, inspects files and applies patches through UnixLocalSandboxClient, or DockerSandboxClient on Windows.
  • Build voice agents two ways — RealtimeAgent holds a WebSocket session with gpt-realtime-2.1, while VoicePipeline chains speech-to-text, an agent workflow and text-to-speech from the optional voice extra.
  • Point it at models other than OpenAI's — The README calls the SDK provider-agnostic across the OpenAI Responses and Chat Completions APIs plus 100+ other LLMs, though every quickstart example still expects OPENAI_API_KEY in the environment.
  • Trace and resume conversations — Tracing is built in for viewing and debugging runs, and Sessions carries conversation history across separate Runner invocations without manual bookkeeping.

Star history

15 Aug to 30 Oct · +1.7k

28.7k30.4k

Frequently asked questions

Is OpenAI Agents SDK free for commercial use?

OpenAI Agents SDK is released under the MIT licence — OSI-approved open source, which permits commercial use.

How can OpenAI Agents SDK be deployed?

OpenAI Agents SDK is available as Self-hosted / Runs locally.

OpenAI Agents SDK
Ask AI
GitHub