OpenAI Agents SDK

pip install "openai-agents[litellm]"

import os
from agents import Agent, Runner, set_tracing_disabled
from agents.extensions.models.litellm_model import LitellmModel

# Disable OpenAI tracing to eliminate OPENAI_API_KEY requirement
set_tracing_disabled(True)

# Initialize agent with Neosantara model
agent = Agent(
    name="Researcher",
    instructions="You are a technology infrastructure analyst providing concise, factual information.",
    model=LitellmModel(model="neosantara/gemini-3.8-flash")
)

result = Runner.run_sync(agent, "Explain the architecture of a regional AI gateway in one paragraph.")
print(result.final_output)

import os
from openai import AsyncOpenAI
from agents import Agent, Runner, set_default_openai_client, set_default_openai_api, set_tracing_disabled

set_tracing_disabled(True)

# Configure global Neosantara client
client = AsyncOpenAI(
    base_url="https://api.neosantara.xyz/v1",
    api_key=os.environ["NEOSANTARA_API_KEY"]
)
set_default_openai_client(client, use_for_tracing=False)
set_default_openai_api("chat_completions")

agent = Agent(
    name="ArchitectBot",
    instructions="Answer technical infrastructure questions with rigorous detail.",
    model="deepseek-v4.1-flash"
)

result = Runner.run_sync(agent, "Compare local regional latency against global API endpoints.")
print(result.final_output)

import os
from openai import AsyncOpenAI
from agents import Agent, Runner, function_tool, set_default_openai_client, set_default_openai_api, set_tracing_disabled

set_tracing_disabled(True)

client = AsyncOpenAI(
    base_url="https://api.neosantara.xyz/v1",
    api_key=os.environ["NEOSANTARA_API_KEY"]
)
set_default_openai_client(client, use_for_tracing=False)
set_default_openai_api("chat_completions")

@function_tool
def check_tier_limits(tier: str) -> str:
    """Check RPM and ITPM rate limit ceilings for a specific Neosantara service tier."""
    limits = {
        "free": "10 RPM, 30,000 ITPM",
        "basic": "50 RPM, 500,000 ITPM",
        "standard": "1,000 RPM, 2,000,000 ITPM"
    }
    return limits.get(tier.lower(), "Tier not found.")

agent = Agent(
    name="QuotaSupport",
    instructions="Use check_tier_limits to answer user questions about throughput limits.",
    model="gemini-3.8-flash",
    tools=[check_tier_limits]
)

result = Runner.run_sync(agent, "What are the rate limits for the Basic tier?")
print(result.final_output)

import os
from openai import AsyncOpenAI
from agents import Agent, Runner, set_default_openai_client, set_default_openai_api, set_tracing_disabled

set_tracing_disabled(True)

client = AsyncOpenAI(
    base_url="https://api.neosantara.xyz/v1",
    api_key=os.environ["NEOSANTARA_API_KEY"]
)
set_default_openai_client(client, use_for_tracing=False)
set_default_openai_api("chat_completions")

# Specialist agent for complex debugging
code_specialist = Agent(
    name="CodeSpecialist",
    instructions="You specialize in systems debugging and algorithm optimization. Resolve code issues thoroughly.",
    model="deepseek-v4.1-flash"
)

# Frontline triage agent
triage_agent = Agent(
    name="TriageAgent",
    instructions="Evaluate incoming requests. If the query requires code debugging or system architecture advice, hand off to CodeSpecialist.",
    model="gemini-3.8-flash",
    handoffs=[code_specialist]
)

result = Runner.run_sync(triage_agent, "I have a race condition in my Go concurrency pool, please help optimize it.")
print(result.final_output)