# openai/openai-agents-python

A lightweight, powerful framework for multi-agent workflows

Repository: https://github.com/openai/openai-agents-python
Canonical: https://ross.abutalabs.com/products/openai-agents-python
Homepage: https://openai.github.io/openai-agents-python/
Language: Python
License: MIT
License Family: permissive
Topics: agents, ai, framework, llm, python, openai, harness
Last push: 2026-08-27T00:05:07+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 38
- inputs: {"age_days": 540, "days_push": 7, "days_rel": 14, "gap_med": 2, "n_releases_24m": 118}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 28982, forks 4605 (observed 2026-08-28T04:11:52.984279+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, tracing, mcp, speech-recognition, tts, chatbot
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: multi-agent, handoffs, guardrails, voice-agents, openai, provider-agnostic, orchestration, ai-agents

## Member repositories
- openai/openai-agents-python (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:52.984279+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:53:16.079918+00:00, confidence not recorded.
  - readme: https://github.com/openai/openai-agents-python (fetched 2026-08-28T04:11:52.984279+00:00, sha ac723f802325)
  - homepage: https://openai.github.io/openai-agents-python/ (fetched 2026-08-29T07:50:23.529341+00:00, sha aec8605044eb)
- Data as of 2026-08-30T08:39:29.467469+00:00.