Skip to main content
The OpenAI Agents SDK provides a lightweight framework for building agents with tool use, handoffs between agents, and input/output guardrails. 
from agents import Agent, Runner

agent = Agent(
    name="assistant",
    instructions="You are a helpful assistant.",
)

while True:
    try:
        user_input = input()
    except EOFError:
        break
    result = Runner.run_sync(agent, user_input)
    print(result.final_output)

openai-agents

superserve deploy agent.py     # or agent.ts
superserve secrets set my-agent OPENAI_API_KEY=sk-...
superserve run my-agent
Runner.run_sync blocks until the full response is ready. For token-by-token streaming, use Runner.run_streamed instead - see the OpenAI Agents SDK streaming docs.
See the full example in Python or TypeScript. Integrate deployed agents into your apps using the Superserve SDK.