[{"data":1,"prerenderedAt":12},["ShallowReactive",2],{"stack-tr-en-openai-agents-sdk":3},{"tagline":4,"description":5,"strengths":6,"useCase":11},"OpenAI's open-source SDK for building tool-using LLM agents that hand off to each other.","The OpenAI Agents SDK is an open-source framework (Python, TypeScript) for building agents from a small set of primitives: agents, tools (functions, web search, MCP servers), handoffs between agents, and guardrails that validate inputs and outputs. Its run loop handles tool calls and delegation, with built-in tracing to debug and evaluate every run. It's our choice when an application runs on OpenAI models and needs to move from an agent prototype to a readable multi-agent system.",[7,8,9,10],"Minimal primitives: agents, tools, handoffs, guardrails and sessions.","Native handoffs: one agent delegates to a specialist with no plumbing.","Input and output guardrails that validate or block, run in parallel.","Built-in tracing, hosted tools (web search, files) and MCP servers.","Multi-agent assistants, automated customer support, research agents and tool-driven workflows.",1792765052026]