Skip to content

Bring Your Framework Agent

Outcome: your framework agent runs through Conductor and produces an inspectable execution.

This page is for agents you have already built in another framework, such as OpenAI Agents, LangChain, LangGraph, or Google ADK. A bridge is the SDK adapter that lets Conductor run such an agent: you keep the agent object your framework already defines, and the bridge runs it as a durable, inspectable Conductor execution. If you are starting from scratch instead, build a native agent with Your First Agent.

Bring your existing agent.

OpenAI Agents LangChain Google ADK Vercel AI SDK

Prerequisites

First, complete Connect to Conductor so the runtime can reach your server. Then make sure the server can call your model provider. On Developer Edition, add the provider as an AI/LLM integration; on a local server, export the provider API key before starting it. Each framework section below begins with the install command for its bridge. Most examples use an OpenAI model, and the Google ADK example uses Gemini, so supply the matching credentials.

OpenAI Agents SDK

Install the agent bridge and OpenAI Agents SDK:

pip install conductor-python

Save as openai_agent.py:

from conductor.ai import Runner
from agents import Agent, function_tool

@function_tool
def get_weather(city: str) -> str:
    return f"72F and sunny in {city}"

agent = Agent(
    name="weather_assistant",
    model="gpt-4o-mini",
    tools=[get_weather],
    instructions="You are a helpful assistant.",
)

result = Runner.run_sync(agent, "What's the weather in NYC?")
print(result.final_output)

Run python openai_agent.py, then verify the output and execution in the UI. The only runner import changes: use conductor.ai.Runner rather than the framework runner.

LangChain

Install the LangChain bridge:

pip install 'conductor-python[langchain]'

from conductor.ai.agents import AgentRuntime
from langchain.agents import create_agent
from langchain_core.tools import tool

@tool
def check_token() -> str:
    """Check a token."""
    return "available"

agent = create_agent("openai:gpt-4o-mini", tools=[check_token],
                     system_prompt="You are a helpful assistant.")

with AgentRuntime() as runtime:
    result = runtime.run(agent, "Is the token set?")
    result.print_result()

LangGraph

Install the LangGraph bridge:

pip install 'conductor-python[langgraph]'

import math
from conductor.ai.agents import AgentRuntime
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent

@tool
def calculate(expression: str) -> str:
    """Evaluate a limited math expression."""
    return str(eval(expression, {"__builtins__": {}}, {"sqrt": math.sqrt, "pi": math.pi}))

graph = create_react_agent(
    ChatOpenAI(model="gpt-4o-mini", temperature=0), tools=[calculate], name="math_agent"
)

with AgentRuntime() as runtime:
    result = runtime.run(graph, "What is sqrt(256) + 2**10?")
    result.print_result()

Google ADK

Install the Google ADK bridge:

python -m pip install 'conductor-python[adk]'

from conductor.ai.agents import AgentRuntime
from google.adk.agents import Agent

agent = Agent(
    name="adk_greeter",
    model="gemini-2.0-flash",
    instruction="You are friendly and concise.",
)

with AgentRuntime() as runtime:
    result = runtime.run(agent, "Say hello and share an ML fact.")
    result.print_result()

Save the file as adk_agent.py and run python adk_agent.py.

Verify and recover

For every bridge, verify the printed result and find the corresponding execution in the Conductor UI. If it fails, first check the runtime server URL, framework package, and provider credentials; then inspect the failed task before retrying. Do not retry an agent action that may have performed an external side effect until its idempotency and recovery policy are clear.

Next production step

Next: every entry in Design Patterns → Agent Recipes is a complete, runnable example — handoffs, memory, guardrails, parallel agents, and more.

Use the production agent architecture to add governance, evaluations, deployment, composition, and operations. The Python SDK framework-agent guide remains the source for the current bridge API and support matrix.

SDK examples

Use the maintained SDK examples for complete, runnable projects. A dash marks a pairing with no maintained example.

Framework Python Java TypeScript / JavaScript C#
OpenAI Agents Examples Examples Examples Examples
Google ADK Examples Examples Examples Examples
LangChain Examples LangChain4j examples Examples —
LangGraph Examples LangGraph4j examples Examples —
Vercel AI SDK — — Examples —