Engine- Python
- JavaScript
Installation
Requires Python SDK version
langsmith>=0.3.15.pip install "langsmith[openai-agents]"
uv add "langsmith[openai-agents]"
Environment configuration
Shell
export LANGSMITH_API_KEY=<your-api-key>
export OPENAI_API_KEY=<your-openai-api-key>
# Optional: set a project for your traces
export LANGSMITH_PROJECT=<your-project-name>
# For LangSmith API keys linked to multiple workspaces, set the LANGSMITH_WORKSPACE_ID environment variable to specify which workspace to use.
export LANGSMITH_WORKSPACE_ID=<your-workspace-id>
Quick start
Integrate LangSmith tracing with the OpenAI Agents SDK by using theOpenAIAgentsTracingProcessor class.import asyncio
from agents import Agent, Runner, set_trace_processors
from langsmith.integrations.openai_agents_sdk import OpenAIAgentsTracingProcessor
async def main():
agent = Agent(
name="Captain Obvious",
instructions="You are Captain Obvious, the world's most literal technical support agent.",
)
question = "Why is my code failing when I try to divide by zero? I keep getting this error message."
result = await Runner.run(agent, question)
print(result.final_output)
if __name__ == "__main__":
set_trace_processors([OpenAIAgentsTracingProcessor()])
asyncio.run(main())
Installation
Requires JS SDK version
langsmith>=0.5.25.npm install langsmith @openai/agents zod
yarn add langsmith @openai/agents zod
pnpm add langsmith @openai/agents zod
Environment configuration
Shell
export LANGSMITH_API_KEY=<your-api-key>
export OPENAI_API_KEY=<your-openai-api-key>
# Optional: set a project for your traces
export LANGSMITH_PROJECT=<your-project-name>
# For LangSmith API keys linked to multiple workspaces, set the LANGSMITH_WORKSPACE_ID environment variable to specify which workspace to use.
export LANGSMITH_WORKSPACE_ID=<your-workspace-id>
Installing
OpenAIAgentsTracingProcessor is an explicit opt-in to tracing. The processor posts traces even when LANGSMITH_TRACING is not set, and nested traceable calls inside agent tools inherit the active trace context.Quick start
RegisterOpenAIAgentsTracingProcessor with the OpenAI Agents SDK before running agents.import { Agent, run, setTraceProcessors, tool } from "@openai/agents";
import { z } from "zod";
import { OpenAIAgentsTracingProcessor } from "langsmith/wrappers/openai_agents";
setTraceProcessors([new OpenAIAgentsTracingProcessor()]);
const getWeather = tool({
name: "get_weather",
description: "Get the current weather for a city",
parameters: z.object({
city: z.string().describe("The city to get weather for"),
}),
execute: async ({ city }: { city: string }) => {
return `The weather in ${city} is sunny.`;
},
});
const agent = new Agent({
name: "WeatherAgent",
instructions: "You are a helpful assistant. Use the get_weather tool when asked about weather.",
model: "gpt-5-nano",
tools: [getWeather],
});
const result = await run(agent, "What's the weather in San Francisco?");
console.log(result.finalOutput);
Configure the processor
Pass options to the processor to set a LangSmith client, project, tags, metadata, or root trace name.import { Agent, run, setTraceProcessors } from "@openai/agents";
import { Client } from "langsmith";
import { OpenAIAgentsTracingProcessor } from "langsmith/wrappers/openai_agents";
const client = new Client();
const processor = new OpenAIAgentsTracingProcessor({
client,
projectName: "openai-agents-demo",
name: "Support agent workflow",
tags: ["openai-agents"],
metadata: {
environment: "development",
},
});
setTraceProcessors([processor]);
const agent = new Agent({
name: "SupportAgent",
instructions: "You are a concise support agent.",
model: "gpt-5-nano",
});
const result = await run(agent, "Help me reset my password.");
console.log(result.finalOutput);
Nest traceable calls in tools
You can use traceable inside OpenAI Agents SDK tool handlers. LangSmith nests those runs under the active tool span.import { Agent, run, setTraceProcessors, tool } from "@openai/agents";
import { z } from "zod";
import { traceable } from "langsmith/traceable";
import { OpenAIAgentsTracingProcessor } from "langsmith/wrappers/openai_agents";
setTraceProcessors([new OpenAIAgentsTracingProcessor()]);
const lookupOrder = traceable(
async (orderId: string) => {
return { orderId, status: "shipped" };
},
{ name: "lookup_order" }
);
const orderStatus = tool({
name: "order_status",
description: "Look up the status of an order",
parameters: z.object({
orderId: z.string().describe("The order ID to look up"),
}),
execute: async ({ orderId }: { orderId: string }) => {
return JSON.stringify(await lookupOrder(orderId));
},
});
const agent = new Agent({
name: "OrdersAgent",
instructions: "Use the order_status tool to answer order questions.",
model: "gpt-5-nano",
tools: [orderStatus],
});
await run(agent, "Where is order 123?");
Flush traces in serverless environments
When tracing in serverless environments, flush pending traces before the process exits.import { Agent, run, setTraceProcessors } from "@openai/agents";
import { Client } from "langsmith";
import { OpenAIAgentsTracingProcessor } from "langsmith/wrappers/openai_agents";
const client = new Client();
const processor = new OpenAIAgentsTracingProcessor({ client });
setTraceProcessors([processor]);
try {
const agent = new Agent({
name: "SupportAgent",
instructions: "You are a concise support agent.",
model: "gpt-5-nano",
});
const result = await run(agent, "Help me reset my password.");
console.log(result.finalOutput);
} finally {
await processor.forceFlush();
}
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.