openai-agents
OpenAI Agents SDK
Decision gist · record as of 2026-08-14
Yes. The SDK is actively maintained, MIT-licensed, has low install friction, supports modern Python versions, and integrates cleanly with openai and pydantic. It is well-suited for developers building multi-agent LLM workflows, especially those needing voice, realtime, or sandbox execution. No known security vulnerabilities as of the fact sheet date.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or newer.
- Set OPENAI_API_KEY environment variable before running agents.
- Low friction install with a pure-Python wheel.
License · maintenance · safety
MIT (permissive) — MIT license permits unrestricted use, modification, and distribution with minimal attribution requirements.
last release 2026-08-11 (3 days) · last repo commit 2026-08-14 · 28,623 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 35,205,039 downloads/mo, #750 on PyPI
Alternatives
Verify before relying
pip install openai-agents
from agents import Agent, Runner
agent = Agent(name="Assistant", instructions="You are a helpful assistant")
result = Runner.run_sync(agent, "Write a haiku about recursion in programming.")
print(result.final_output)- Whether the 100+ LLM providers claim includes both OpenAI and non-OpenAI models equally
- Performance characteristics and latency expectations for realtime agents over WebSocket
- Whether sandbox agents work on Windows without the Docker extra or a hosted client
What it is and what it does
The OpenAI Agents SDK is a Python framework for building multi-agent workflows that coordinate LLM-powered agents with tools, guardrails, and handoffs. It supports four primary execution modes: text agents for stateless workflows, sandbox agents for long-running tasks with file and command access, realtime agents for low-latency voice over WebSocket, and voice pipelines that combine speech-to-text, agent logic, and text-to-speech. Agents can delegate to other agents, invoke tools (functions, MCP, or hosted), validate inputs and outputs with guardrails, maintain conversation history across runs, and involve humans at decision points. The framework depends on openai, pydantic, requests, websockets, mcp, griffelib, and typing-extensions, and integrates with optional extras for voice support and Redis session storage.
Use it for
- Build a text-based assistant that answers questions and delegates complex tasks to specialized sub-agents
- Create a sandbox agent that inspects a Git repository, runs tests, and applies code patches autonomously
- Develop a voice agent using gpt-realtime-2.1 for low-latency conversational AI over WebSocket
- Combine speech-to-text, an agent workflow, and text-to-speech into a voice pipeline for audio interaction
- Implement guardrails to validate and sanitize agent inputs and outputs before execution or user delivery
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The SDK is actively maintained, MIT-licensed, has low install friction, supports modern Python versions, and integrates cleanly with openai and pydantic. It is well-suited for developers building multi-agent LLM workflows, especially those needing voice, realtime, or sandbox execution. No known security vulnerabilities as of the fact sheet date.
Install
openai-agents on PyPI
Before you install
Low friction install with a pure-Python wheel. Active maintenance with a release 3 days ago and 28623 repository stars. Requires Python 3.10 or newer.
Requires Python 3.10 or newer. Set OPENAI_API_KEY environment variable before running agents.
License in practice
MIT license permits unrestricted use, modification, and distribution with minimal attribution requirements.
Quickstart
pip install openai-agents
from agents import Agent, Runner
agent = Agent(name="Assistant", instructions="You are a helpful assistant")
result = Runner.run_sync(agent, "Write a haiku about recursion in programming.")
print(result.final_output)Verify before relying
- Whether the 100+ LLM providers claim includes both OpenAI and non-OpenAI models equally
- Performance characteristics and latency expectations for realtime agents over WebSocket
- Whether sandbox agents work on Windows without the Docker extra or a hosted client
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packagesgriffelibmcpopenaipydanticrequeststyping-extensionswebsockets |
| Maintenance | Actively maintained 3 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 35,205,039 / month, #750 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Software Development :: Libraries :: Python ModulesTyping :: Typed |
Evidence: openai_agents-0.20.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “voice agent builder”
- openai-agentsA framework for building multi-agent LLM workflows with support for…
- strands-agentsStrands Agents is a Python SDK for building AI agents that work with…
- livekit-plugins-sileroProvides Silero voice activity detection integration for the LiveKit…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also composio-openai-agents · smolagents · openinference-instrumentation-openai-agents · openai-guardrails · opentelemetry-instrumentation-openai-agents · agentscope · praisonaiagents · livekit-agents · PraisonAI · agent-framework-devui