Guide

Monitor your LangGraph agents in production.

A LangGraph agent loops through nodes, calls tools and hits the model several times per run. AgentPing rides LangChain's callback system, so one record lands per graph run with the cost, status and output behind it, no graph rewrites.

Track your first AI workflow Jump to setup

Two lines, then every run reports in.

Install the SDK and point it at your LangGraph agent. One record lands per run with the cost, status, latency and output behind it.

shellinstall
pip install agentping
pythonmonitor your agent
import agentping
from agentping import AgentPingCallbackHandler

agentping.init(api_key="apk_…", agent="research-graph")

# LangGraph runs on LangChain's callback system, so pass the handler
# in config and every node, tool call and model call is captured.
result = graph.invoke(
    {"messages": [("user", "…")]},
    config={"callbacks": [AgentPingCallbackHandler()]},
)

The handler captures token usage and cost from the underlying model calls and ties them to one run per graph invocation. Full reference is in the docs.

What AgentPing tracks for LangGraph.

  • Cost per graph run, attributed to the customer and feature you tag.
  • A missed-run alert when a scheduled graph stops firing.
  • Output quality on the final answer, scored against a rubric you write in plain English.

See the pillars behind these: Spend, Pulse and Verify. For why teams monitor LangGraph with AgentPing, see the LangGraph integration.

Do I have to rewrite my graph?
No. LangGraph uses LangChain's callback system, so you pass AgentPingCallbackHandler in the config callbacks and the existing graph is captured as-is. One record lands per graph invocation.
Does it slow the graph down?
No. Telemetry runs off the hot path with a hard 2-second timeout and a bounded local queue. If AgentPing is unreachable the graph runs exactly as if the SDK were not installed.
Can I see cost per node?
The run rolls up the cost of every model call in the graph. Tag a run with customer and feature at the start and the spend is attributed that way across the dashboard.

Monitor your LangGraph agents in minutes.

Add the SDK, send one run, and watch cost, status and quality land in the dashboard.

Track your first AI workflow All monitoring guides