openai-agents
Expert guidance for building AI agents with the OpenAI Agents SDK, from simple single-agent systems to complex multi-agent workflows. Use when working with: (1) Creating AI agents with tools and structured outputs, (2) Multi-agent orchestration with handoffs or manager patterns, (3) Agent guardrails and validation, (4) Conversation history with sessions, (5) Tracing and debugging agent workflows, (6) Tool integration and context management, (7) Production-ready agent systems. Supports async Python with comprehensive examples and patterns.
npx skills add majiayu000/claude-skill-registry --skill openai-agents-psqasim-personal-ai-employee --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# OpenAI Agents SDK Build AI agent systems from simple single-agent tools to complex multi-agent orchestrations using the official OpenAI Agents SDK. ## Installation and Setup Install the SDK: ```bash pip install openai-agents ``` Set your API key: ```bash export OPENAI_API_KEY=sk-... ``` All agent workflows are asynchronous. Use `asyncio.run()` or `await` in async contexts: ```python import asyncio from agents import Agent, Runner async def main(): agent = Agent(name="Assistant", instructions="Be helpful") result = await Runner.run(agent, "Hello!") print(result.final_output) if __name__ == "__main__": asyncio.run(main()) ``` ## Agent Development Workflow Follow this progression based on complexity: **1. Single Agent** → Start here for straightforward tasks (Q&A, analysis, generation) **2. Agent with Tools** → Add when agents need to fetch data or perform actions **3. Agent with Structured Output** → Use when you need validated, typed responses **4. Multi-Agent System** → Scale when tasks require specialization or orchestration ## Quick Start: Single Agent Create a basic agent with custom instructions: ```python from agents import Agent, Runner import asyncio agent = Agent( name="M
- Installation and Setup
- Agent Development Workflow
- Quick Start: Single Agent
- Adding Tools to Agents
- Structured Output with Pydantic
- Multi-Agent Systems
- Pattern 1: Manager/Orchestrator (Agents as Tools)
- Pattern 2: Peer Handoffs
- Guardrails for Safety and Validation
- Session Management for Conversation Memory
- Context Management
- Error Handling
- Tracing and Debugging
- Reference Documentation
pip install openai-agents export OPENAI_API_KEY=sk-... export OPENAI_AGENTS_DISABLE_TRACING=1
What does the openai-agents skill do?
Expert guidance for building AI agents with the OpenAI Agents SDK, from simple single-agent systems to complex multi-agent workflows. Use when working with: (1) Creating AI agents with tools and structured outputs, (2) Multi-agent orchestration with handoffs or manager patterns, (3) Agent guardrails and validation, (4) Conversation history with sessions, (5) Tracing and debugging agent workflows, (6) Tool integration and context management, (7) Production-ready agent systems. Supports async Python with comprehensive examples and patterns.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill openai-agents-psqasim-personal-ai-employee --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.