VerifiedPlugin
Development
codex
Lightweight coding agent that runs in your terminal
6 skills
@openaiDevelopment
Plugin
openai-agents-python
The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows. It is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs, as well as 100+ other LLMs. Looking for the JavaScript/TypeScript version?
Plugin Signal70/100Solid
maintained100
capable37
documented50
adopted95
Stats
28,536
Stars
4,475
Forks
Active
Maintenance
Python
Language
MIT
License
2m ago
Last commit
1y ago
Created
Repo: openai/openai-agents-python
What's inside
Agents
5promptYou are a general computer-use agent operating in a terminal-based assistant environment. You are expected to be precise, safe, and helpful.memory_consolidation_promptYou are a Memory Writing Agent.memory_read_promptYou have access to a memory folder with guidance from prior runs in this sandbox workspace. It can save time and help you stay consistent. Use it whenever it is likely to help.rollout_extraction_promptYou are a Memory Writing Agent.rollout_extraction_user_messageAnalyze this memory rollout and produce JSON with `raw_memory`, `rollout_summary`, and `rollout_slug` (use empty string when unknown).
README
1OpenAI Agents SDK 
The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows. It is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs, as well as 100+ other LLMs.
[!NOTE] Looking for the JavaScript/TypeScript version? Check out Agents SDK JS/TS.
Core concepts:
- Agents: LLMs configured with instructions, tools, guardrails, and handoffs
- Sandbox agents: Agents preconfigured to work with a container to perform work over long time horizons.
- Realtime agents: Build powerful voice agents with
gpt-realtime-2.1and full agent features - Voice agents: Build voice pipelines that combine speech-to-text, an agent workflow, and text-to-speech
- Agents as tools / Handoffs: Delegating to other agents for specific tasks
- Tools: Various Tools let agents take actions (functions, MCP, hosted tools)
- Guardrails: Configurable safety checks for input and output validation
- Human in the loop: Built-in mechanisms for involving humans across agent runs
- Sessions: Automatic conversation history management across agent runs
- Tracing: Built-in tracking of agent runs, allowing you to view, debug and optimize your workflows
Explore the examples directory to see the SDK in action, and read our documentation for more details.
Get started
To get started, set up your Python environment (Python 3.10 or newer required), and then install OpenAI Agents SDK package.
venv
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
pip install openai-agents
For voice support, install with the optional voice group: pip install 'openai-agents[voice]'. For Redis session support, install with the optional redis group: pip install 'openai-agents[redis]'.
uv
If you're familiar with uv, installing the package would be even easier:
uv init
uv add openai-agents
For voice support, install with the optional voice group: uv add 'openai-agents[voice]'. For Redis session support, install with the optional redis group: uv add 'openai-agents[redis]'.
Run your first agents
The SDK supports four primary ways to run agents. Set the OPENAI_API_KEY environment variable before running any of these examples.
Run a text agent
Use a text Agent for workflows that do not need a persistent realtime connection or a sandbox workspace.
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)
# Code within the code,
# Functions calling themselves,
# Infinite loop's dance.
(For Jupyter notebook users, see hello_world_jupyter.ipynb)
Run a sandbox agent
Use a SandboxAgent when the agent needs to inspect files, run commands, apply patches, or preserve workspace state across longer tasks.
This example uses UnixLocalSandboxClient, which is supported on macOS and Linux. On Windows, use DockerSandboxClient with the openai-agents[docker] extra or a hosted sandbox client instead; see Sandbox clients for setup details.
from agents import Runner
from agents.run import RunConfig
from agents.sandbox import Manifest, SandboxAgent, SandboxRunConfig
from agents.sandbox.entries import GitRepo
from agents.sandbox.sandboxes import UnixLocalSandboxClient
agent = SandboxAgent(
name="Workspace Assistant",
instructions="Inspect the sandbox workspace before answering.",
default_manifest=Manifest(entries={"repo": GitRepo(repo="openai/openai-agents-python", ref="main")}),
)
result = Runner.run_sync(
agent,
"Inspect the repo README and summarize what this project does.",
run_config=RunConfig(sandbox=SandboxRunConfig(client=UnixLocalSandboxClient())),
)
print(result.final_output)
Run a realtime agent
Use a RealtimeAgent for low-latency, server-side voice and multimodal experiences over WebSocket.
import asyncio
from agents.realtime import RealtimeAgent, RealtimeRunner
async def main() -> None:
agent = RealtimeAgent(name="Assistant", instructions="You are a helpful voice assistant. Keep responses short.")
runner = RealtimeRunner(starting_agent=agent)
session = await runner.run()
async with session:
await session.send_message("Say hello in one short sentence.")
async for event in session:
if event.type == "audio":
# Forward or play event.audio.data.
pass
elif event.type == "history_added":
print(event.item)
elif event.type == "agent_end":
break
if __name__ == "__main__":
asyncio.run(main())
Run a voice agent
Use a VoicePipeline to turn audio into text, run an agent workflow, and stream generated speech.
import asyncio
import numpy as np
from agents import Agent
from agents.voice import AudioInput, SingleAgentVoiceWorkflow, VoicePipeline
async def main() -> None:
agent = Agent(name="Assistant", instructions="You are a helpful voice assistant.")
pipeline = VoicePipeline(workflow=SingleAgentVoiceWorkflow(agent))
audio_input = AudioInput(buffer=np.zeros(24000 * 3, dtype=np.int16))
result = await pipeline.run(audio_input)
async for event in result.stream():
if event.type == "voice_stream_event_audio":
# Forward or play event.data.
pass
if __name__ == "__main__":
asyncio.run(main())
Explore the examples directory to see the SDK in action, and read our documentation for more details.
Acknowledgements
We'd like to acknowledge the excellent work of the open-source community, especially:
This library has these optional dependencies:
We also rely on the following tools to manage the project:
We're committed to continuing to build the Agents SDK as an open source framework so others in the community can expand on our approach.
File tree
1455openai/openai-agents-pythonView on GitHub
.agents/
references/
agent-definition-and-run-context.md
conversation-state-ownership.md
function-and-output-schema.md
local-mcp-server-lifecycle.md
model-provider-boundaries.md
README.md
realtime-session-lifecycle.md
realtime-tracing.md
run-item-lifecycle.md
runner-lifecycle.md
runstate-schema.md
sandbox-runtime-boundary.md
session-persistence.md
tool-execution-lifecycle.md
tool-identity.md
tracing-lifecycle.md
voice-pipeline-lifecycle.md
skills/
code-change-verification/
agents/
openai.yaml
scripts/
run.ps1
run.sh
SKILL.md
docs-sync/
agents/
openai.yaml
references/
doc-coverage-checklist.md
SKILL.md
examples-auto-run/
agents/
openai.yaml
scripts/
run.sh
SKILL.md
final-release-review/
agents/
openai.yaml
references/
review-checklist.md
scripts/
find_latest_release_tag.sh
SKILL.md
implementation-final-review/
agents/
openai.yaml
references/
reviewer-brief.md
scripts/
review_protocol.py
review_state.py
test_review_protocol.py
test_review_state.py
test_skill_contract.py
SKILL.md
implementation-kickoff/
agents/
openai.yaml
scripts/
validate_handoff.py
SKILL.md
implementation-strategy/
agents/
openai.yaml
SKILL.md
integration-tests/
agents/
openai.yaml
SKILL.md
maintainer-review/
agents/
openai.yaml
references/
evaluation-framework.md
SKILL.md
openai-knowledge/
agents/
openai.yaml
SKILL.md
pr-draft-summary/
agents/
openai.yaml
SKILL.md
runtime-behavior-probe/
agents/
openai.yaml
references/
error-cases.md
openai-runtime-patterns.md
reporting-format.md
validation-matrix.md
SKILL.md
templates/
python_probe.py
sensitive-logging-audit/
agents/
openai.yaml
references/
redaction-validation.md
scripts/
inventory_logging.py
test_inventory.py
SKILL.md
test-coverage-improver/
agents/
openai.yaml
SKILL.md
.github/
dependabot.yml
ISSUE_TEMPLATE/
bug_report.md
feature_request.md
model_provider.md
question.md
PULL_REQUEST_TEMPLATE/
pull_request_template.md
scripts/
check_optional_truthiness.py
detect-changes.sh
run_integration_tests.py
run_serial_tests.py
run-asyncio-teardown-stability.sh
select-release-milestone.py
update_rclone_pin.py
workflows/
docs.yml
issues.yml
publish.yml
release-pr.yml
release-tag.yml
tests.yml
.gitignore
.prettierrc
.vscode/
launch.json
settings.json
AGENTS.md
CLAUDE.md
docs/
agents.md
assets/
images/
favicon-platform.svg
graph.png
harness_with_compute.png
mcp-tracing.jpg
orchestration.png
logo.svg
config.md
context.md
examples.md
guardrails.md
handoffs.md
human_in_the_loop.md
index.md
ja/
agents.md
config.md
context.md
examples.md
guardrails.md
handoffs.md
human_in_the_loop.md
index.md
mcp.md
models/
index.md
litellm.md
multi_agent.md
quickstart.md
realtime/
guide.md
quickstart.md
transport.md
release.md
repl.md
results.md
running_agents.md
sandbox/
sandbox_agents.md
clients.md
guide.md
memory.md
sessions/
sessions.md
advanced_sqlite_session.md
encrypted_session.md
index.md
sqlalchemy_session.md
streaming.md
tools.md
tracing.md
usage.md
visualization.md
voice/
pipeline.md
quickstart.md
tracing.md
ko/
agents.md
config.md
context.md
examples.md
guardrails.md
handoffs.md
human_in_the_loop.md
index.md
mcp.md
models/
index.md
litellm.md
multi_agent.md
quickstart.md
realtime/
guide.md
quickstart.md
transport.md
release.md
repl.md
results.md
running_agents.md
sandbox/
sandbox_agents.md
clients.md
guide.md
memory.md
sessions/
sessions.md
advanced_sqlite_session.md
encrypted_session.md
index.md
sqlalchemy_session.md
streaming.md
tools.md
tracing.md
usage.md
visualization.md
voice/
pipeline.md
quickstart.md
tracing.md
llms-full.txt
llms.txt
mcp.md
models/
index.md
litellm.md
multi_agent.md
quickstart.md
realtime/
guide.md
quickstart.md
transport.md
ref/
agent_output.md
agent_tool_input.md
agent_tool_state.md
agent.md
apply_diff.md
computer.md
decorators.md
editor.md
exceptions.md
extensions/
experimental/
codex/
codex_options.md
codex_tool.md
codex.md
events.md
exec.md
items.md
output_schema_file.md
payloads.md
thread_options.md
thread.md
turn_options.md
hosted_multi_agent/
model.md
handoff_filters.md
handoff_prompt.md
litellm.md
memory/
advanced_sqlite_session.md
async_sqlite_session.md
dapr_session.md
encrypt_session.md
mongodb_session.md
redis_session.md
sqlalchemy_session.md
models/
any_llm_model.md
any_llm_provider.md
litellm_model.md
litellm_provider.md
sandbox/
blaxel/
mounts.md
sandbox.md
cloudflare/
mounts.md
sandbox.md
daytona/
mounts.md
sandbox.md
e2b/
mounts.md
sandbox.md
modal/
mounts.md
sandbox.md
runloop/
mounts.md
sandbox.md
vercel/
mounts.md
sandbox.md
tool_output_trimmer.md
visualization.md
function_schema.md
guardrail.md
handoffs/
handoffs.md
history.md
index.md
items.md
lifecycle.md
logger.md
mcp/
manager.md
server.md
util.md
memory/
memory.md
openai_conversations_session.md
openai_responses_compaction_session.md
session_settings.md
session.md
sqlite_session.md
util.md
model_settings.md
models/
chatcmpl_converter.md
chatcmpl_helpers.md
chatcmpl_stream_handler.md
default_models.md
fake_id.md
interface.md
multi_provider.md
openai_agent_registration.md
openai_chatcompletions.md
openai_client_utils.md
openai_provider.md
openai_responses.md
reasoning_content_replay.md
prompts.md
realtime/
agent.md
audio_formats.md
config.md
events.md
handoffs.md
items.md
model_events.md
model_inputs.md
model.md
openai_realtime.md
runner.md
session.md
repl.md
responses_websocket_session.md
result.md
retry.md
run_config.md
run_context.md
run_error_handlers.md
run_internal/
agent_bindings.md
agent_runner_helpers.md
approvals.md
error_handlers.md
guardrails.md
items.md
model_retry.md
oai_conversation.md
prompt_cache_key.md
run_grouping.md
run_loop.md
run_steps.md
session_persistence.md
streaming.md
tool_actions.md
tool_caller.md
tool_execution.md
tool_planning.md
tool_use_tracker.md
... 1309 moreMore Flows by @openai.
@openaiVerifiedPlugin
Development
codex-plugin-cc
Use Codex from inside Claude Code for code reviews or to delegate tasks to Codex. This plugin is for Claude Code users who want an easy way to start using Codex from the workflow they already have.
3 skills
@openaiFAQ
openai-agents-python is a Claude Code plugin with hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is openai-agents-python?
- The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows. It is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs, as well as 100+ other LLMs. Looking for the JavaScript/TypeScript version?
- How do I install openai-agents-python?
- Run these in Claude Code: . Then prompt normally.
- Does openai-agents-python auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is openai-agents-python free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.