Trace LangGraph with BotGauge

Records LangGraph graph, node, and LLM spans. LangGraph uses the LangChain instrumentor.


Extra	`[langgraph]`
Verified framework versions	langgraph 1.2.11 and 1.2.16
Instrumentor installed by the extra	`openinference-instrumentation-langchain 0.1.79`
Zero-code run	Traced

Also verified: langgraph 1.2.11 with instrumentor 0.1.76. The extra no longer installs that older instrumentor. See supported frameworks for how verification works.

In code

Call tracing.init(), attach the framework instrumentor to the provider it returns, and wrap the work in tracing.turn() and tracing.agent().

Install

terminal

pip install "botgauge[langgraph]" langgraph==1.2.16 langchain-openai==1.7.2

Add the code

app.py

import os

from botgauge import tracing
from langchain_openai import ChatOpenAI
from langgraph.graph import END, START, MessagesState, StateGraph
from openinference.instrumentation.langchain import LangChainInstrumentor

provider = tracing.init()
LangChainInstrumentor().instrument(tracer_provider=provider)

llm = ChatOpenAI(model=os.environ["OPENAI_MODEL"])

def supervisor(state: MessagesState) -> dict:
    return {"messages": [llm.invoke(state["messages"])]}

graph = StateGraph(MessagesState)
graph.add_node("supervisor", supervisor)
graph.add_edge(START, "supervisor")
graph.add_edge("supervisor", END)
app = graph.compile()

with tracing.turn(session_id="ses_langgraph"), tracing.agent("supervisor-graph"):
    result = app.invoke({"messages": [("user", "In one sentence, what is OpenTelemetry?")]})
print(result["messages"][-1].text)

tracing.shutdown()

Run

terminal

python app.py

Needs BOTGAUGE_API_KEY, OPENAI_API_KEY, OPENAI_MODEL. Set OPENAI_BASE_URL too if your LLM isn’t api.openai.com.

Zero-code

Leave your app unchanged and start it with botgauge instrument. The sample still wraps the work in tracing.turn() and tracing.agent() so spans carry session and agent ids.

Install

terminal

pip install "botgauge[langgraph]" langgraph==1.2.16 langchain-openai==1.7.2

Add the code

app.py

import os

from botgauge import tracing
from langchain_openai import ChatOpenAI
from langgraph.graph import END, START, MessagesState, StateGraph

llm = ChatOpenAI(model=os.environ["OPENAI_MODEL"])

def supervisor(state: MessagesState) -> dict:
    return {"messages": [llm.invoke(state["messages"])]}

graph = StateGraph(MessagesState)
graph.add_node("supervisor", supervisor)
graph.add_edge(START, "supervisor")
graph.add_edge("supervisor", END)
app = graph.compile()

with tracing.turn(session_id="ses_langgraph"), tracing.agent("supervisor-graph"):
    result = app.invoke({"messages": [("user", "In one sentence, what is OpenTelemetry?")]})
print(result["messages"][-1].text)

Run

terminal

botgauge instrument python app.py

Needs BOTGAUGE_API_KEY, OPENAI_API_KEY, OPENAI_MODEL. Set OPENAI_BASE_URL too if your LLM isn’t api.openai.com.

View LangGraph spans live

Watch your LangGraph graph, node, and LLM spans appear in BotGauge.

Try BotGauge →

See versions not verified if you run a different version, capture and redaction to control exported content, and troubleshooting if spans are missing.

Frameworks

More

Trace LangGraph with BotGauge

In code

Zero-code

​In code

​Zero-code

​Related

In code

Zero-code

Related