openai/openai-agents-python
OpenAI's first-party multi-agent framework: agents, handoffs, guardrails, and tracing in a deliberately small API surface. Agentiquette scores it 79/100 (A-tier), methodology v1.0, scored 2026-07-07.
Key facts
| Category | Orchestration framework |
|---|---|
| License | MIT |
| Maintainer | OpenAI |
| Compatible agents | generic |
| File patterns | |
| Triggering | manual-reference |
| GitHub metrics | 27,705 stars · 4,267 forks · 65 open issues (fetched 2026-07-07) |
| Last commit | 2026-07-07 |
| Created | 2025-03-11 |
Editorial analysis
What a vendor framework looks like when it learns from the ecosystem's first two years: guardrails and tracing are core primitives rather than afterthoughts, and the API resists the bloat that sank earlier frameworks. The handoff model is the cleanest available vocabulary for agent-to-agent delegation.
Risks
Vendor-first design: portable in principle, optimized for one provider in practice.
Evidence notes: Reliability: guardrails as first-class input/output checks. Maintenance: same-day commits, remarkably small issue count. Composability: handoffs compose agents cleanly within the framework's own boundary.
Install and first run
pip install openai-agentsAlternatives in this category
The most adopted graph-based agent orchestration framework: workflows as explicit state machines with checkpointing, human-in-the-loop…
An agent framework built on type validation: structured outputs, dependency injection, and tool schemas checked the way Pydantic checks…
Google's Agent Development Kit: code-first agent construction with built-in evaluation tooling and deployment paths into the Google Cloud…
Embed this badge
Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.
[](https://agentiquette.com/index/repos/openai-agents-python)Frequently asked questions
Is openai/openai-agents-python good?
openai/openai-agents-python scores 79/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.
What is openai/openai-agents-python for?
OpenAI's first-party multi-agent framework: agents, handoffs, guardrails, and tracing in a deliberately small API surface.
Is openai/openai-agents-python maintained?
Last commit 2026-07-07, 65 open issues at fetch time (2026-07-07). Maintenance is scored at 92 of 100.
Maintainer of openai/openai-agents-python? Claim this listing and suggest corrections.