openai/openai-agents-python

Health v2 · maintenance only

Adoption not part of the score

28982 stars · 4605 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

OpenAI Agents SDK is a lightweight Python framework for building multi-agent LLM workflows with agents, handoffs, tools, guardrails, sessions, and built-in tracing. It is provider-agnostic, supporting OpenAI APIs plus 100+ other LLMs, and includes voice and realtime agent support.

Use cases

• build multi-agent llm workflows in python
• orchestrate agents with handoffs and tools
• add guardrails to validate llm inputs and outputs
• build voice agents with speech-to-text and text-to-speech
• trace and debug agent runs
• connect agents to mcp servers
• manage conversation history across agent runs

When to choose

• you want a lightweight, production-ready agent framework with few abstractions
• you need multi-agent coordination via handoffs or agents-as-tools
• you want built-in tracing, guardrails, and human-in-the-loop support
• you want provider-agnostic LLM support beyond OpenAI

When to avoid

• you need a heavyweight orchestration platform with visual workflow editors
• you are building in JavaScript/TypeScript rather than Python
• you only need simple single-prompt LLM calls without agent loops

Facets

framework · maturity active

agent-framework llm-inference tracing mcp speech-recognition tts chatbot artificial-intelligence large-language-models developer-tools python cross-platform multi-agent handoffs guardrails voice-agents openai provider-agnostic orchestration ai-agents

Member repositories

For agents

markdown · JSON · MCP: product_card(name="openai/openai-agents-python")