OpenAI Agents SDK (Python)

Use this skill when developing AI agents using OpenAI Agents SDK (openai-agents package).

Quick Reference

Installation

uv add openai-agents        # or `pip install openai-agents` outside a uv project

Environment Variables

Set both in the process environment before running the example; replace the placeholders:

export OPENAI_API_KEY="sk-..."
export OPENAI_MODEL="your-verified-model-id"

Using Azure or another provider instead? See agents.md — don't hardcode provider env vars here, they vary and go stale.

Basic Agent

import os
from agents import Agent, Runner

agent = Agent(
    name="Assistant",
    instructions="You are a helpful assistant.",
    model=os.environ["OPENAI_MODEL"],  # configure a verified model ID
)

# Synchronous
result = Runner.run_sync(agent, "Tell me a joke")
print(result.final_output)

# Asynchronous
result = await Runner.run(agent, "Tell me a joke")

Omitting model= uses the installed SDK's default. Configure it explicitly in production and verify available IDs against the provider's model catalog.

Key Patterns

The SDK has no separate Subagent class: express delegation with handoffs or agent.as_tool(). For model-written tool orchestration, use ProgrammaticToolCallingTool and verify its Responses-only constraints.

Preferred: Live Docs via MCP

Model names and API details change frequently. When available, consult the OpenAI Developer Docs MCP server (openaiDeveloperDocs) before relying on the static references below.

Setup (Codex CLI):

codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcp

Setup (Claude Code):

claude mcp add --transport http openaiDeveloperDocs https://developers.openai.com/mcp

Or in Codex ~/.codex/config.toml (VS Code and Cursor use different JSON schemas):

[mcp_servers.openaiDeveloperDocs]
url = "https://developers.openai.com/mcp"

Key tools: mcp__openaiDeveloperDocs__search_openai_docs, fetch_openai_doc, list_api_endpoints, get_openapi_spec.

Rules: Cite fetched docs. Never speculate on field names, defaults, or current model IDs — fetch first. Keep quotes under 125 chars.

Fallback when MCP is unavailable: https://developers.openai.com/api/docs/llms.txt (plain-text index of all API docs; each entry has a .md twin at /api/docs/<slug>.md).

Reference Documentation

Offline/quick-lookup snippets. Verify model names and API signatures against the MCP or docs when accuracy matters.

• agents.md - read when choosing or wiring a model: default-model caveat, LiteLLM, native Azure client
• tools.md - read when adding function tools, hosted tools, or agents-as-tools
• structured-output.md - read when the output must be a Pydantic/dataclass shape (AgentOutputSchema, strict vs non-strict)
• streaming.md - read when streaming to a UI (event types, SSE with FastAPI)
• handoffs.md - read when one agent delegates to another (handoff vs as_tool, input filters)
• guardrails.md - read when validating input/output or gating tool calls
• sessions.md - read when conversation history must persist across requests (SQLite, SQLAlchemy, Redis, OpenAI Conversations)
• patterns.md - read for multi-agent pipelines, LLM-as-judge loops, tracing controls, max_turns, parallelization
• sandbox.md - read when the agent must edit files or run commands in an isolated workspace (SandboxAgent, beta)

Official Documentation

• Docs: https://openai.github.io/openai-agents-python/
• Examples: https://github.com/openai/openai-agents-python/tree/main/examples
• Major update: https://openai.com/index/the-next-evolution-of-the-agents-sdk/
• Docs MCP setup: https://developers.openai.com/learn/docs-mcp
• Docs index (llms.txt): https://developers.openai.com/api/docs/llms.txt
• Current model IDs: https://platform.openai.com/docs/models