AI Frameworks

OpenAI Agents SDK

Python and TypeScript framework for multi-agent workflows. Agent handoffs, tool use, guardrails, sessions, tracing. Provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs plus 100+ other LLMs.

Try OpenAI Agents SDKopenai.com/index/agents-sdk

Save

The OpenAI Agents SDK (the production successor to Swarm) is a minimal Python framework for building multi-agent systems. Core concepts: Agents (an LLM + instructions + tools), Handoffs (agents delegating to specialists), Guardrails (input/output validation), and Tracing (built-in observability). It's deliberately lightweight - no heavy abstractions or state management. You define agents as simple Python objects, wire them together with handoffs, and the SDK handles the orchestration. It works with any OpenAI model and supports streaming. Good for building customer service bots, research agents, and workflow automation.

ai framework agents openai python multi-agent

OpenAI Agents SDK at a glance

Last verified October 17, 2026

Pricing: Agents SDK - free and open source under MIT (Python and TypeScript)
Models - pay per token at OpenAI API rates, or at your provider's rates through the beta Any-LLM and LiteLLM adapters
Install: pip install openai-agents
uv add openai-agents
npm install @openai/agents zod
Models: An agent with no model set runs on gpt-5.6-luna, with reasoning effort none and low verbosity. You can override that per agent, per run through RunConfig, or for everything with the OPENAI_DEFAULT_MODEL environment variable. Non-OpenAI models run through the Any-LLM and LiteLLM adapters, which are best-effort betas, and MultiProvider can route on model-name prefixes.
Recent changes: Oct 15v0.24.0 exposes MCP annotations on converted tools, adds run-wide tool exception formatting, and defers automatic compaction while approvals are pending.
Oct 2v0.23.0 adds configurable MCP listing page limits, opt-in Docker removal protection and configurable memory consolidation turns for sandboxes, and an opt-in encrypted history scan budget for sessions.
Sep 17v0.22.3 aligns conditional approvals with validated tool arguments and fixes server-managed resume, POSIX command paths on Windows sandbox hosts, and concurrent async SQLite session startup.

Sources: openai/openai-agents-python README, openai-agents-python releases, Agents SDK models docs, openai/openai-agents-js README

Similar Tools

AI Frameworks

Agency Swarm

Multi-agent orchestration framework built on the OpenAI Agents SDK. Define agent roles, typed tools, and directional communication flows. Production-focused, open-source.

AI Frameworks

CrewAI

Multi-agent orchestration framework. Define agents with roles, goals, and tools, then assign them tasks in a crew. Python-based. Great for complex workflows.

AI Frameworks

Claude Agent SDK

Anthropic's SDK for building agents on the same tools, agent loop, and context management that power Claude Code. Python and TypeScript. Subagents, hooks, MCP, and permissions.

AI Frameworks

LangChain / LangGraph

Most popular LLM framework. 100K+ GitHub stars. Chains, RAG, vector stores, tool use. LangGraph adds stateful multi-agent workflows with cycles and persistence.

Get started with OpenAI Agents SDK

Try OpenAI Agents SDK

Get weekly tool reviews

Honest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.

Subscribe Free

Compare all pricing Compare side by side

More AI Frameworks Tools

Vercel AI SDK

The TypeScript toolkit for building AI apps. Unified API across OpenAI, Anthropic, Google. Streaming, tool calling, structured output, multi-step agents. 27K+ GitHub stars.

CopilotKit

Frontend stack for agent-native apps. React hooks, prebuilt copilot UI, AG-UI runtime, frontend tools, shared state, and human-in-the-loop flows.

Claude Agent SDK

Anthropic's SDK for building agents on the same tools, agent loop, and context management that power Claude Code. Python and TypeScript. Subagents, hooks, MCP, and permissions.