OpenAI Agents SDK Python多智能体工作流框架
The OpenAI Agents SDK is a lightweight Python framework for building multi-agent workflows. It supports 100+ LLMs, provides built-in guardrails, handoffs between agents, MCP tool integration, tracing, sessions, and real-time voice capabilities.
Installation
Use the upstream install or setup path that matches your environment:
- pip install openai-agents
- uv init
- uv add openai-agents
Requirements and caveats from upstream:
- Agents: LLMs configured with instructions, tools, guardrails, and handoffs
- Sandbox Agents: Agents preconfigured to work with a container to perform work over long time horizons.
- Agents as tools / Handoffs: Delegating to other agents for specific tasks
Basic usage or getting-started notes:
- ## Run your first Sandbox Agent
- from agents.run import RunConfig
- # Run this agent on the local filesystem
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/openai/openai-agents-python/HEAD/README.md
