Guide

Monitor your OpenAI Agents SDK agents.

Agents built with the OpenAI Agents SDK hand off between agents, run tools and call the model in a loop. AgentPing hooks into that lifecycle so one record lands per run with the cost, status and output behind it.

Track your first AI workflow Jump to setup

Two lines, then every run reports in.

Install the SDK and point it at your OpenAI Agents SDK 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 AgentPingHooks
from agents import Agent, Runner

agentping.init(api_key="apk_…", agent="support-triage")

agent = Agent(name="triage", instructions="…")

# Pass the hooks; hand-offs, tool calls and model calls are captured.
result = await Runner.run(agent, input="…", hooks=AgentPingHooks())

AgentPingHooks plugs into the SDK's run lifecycle, so a single run that hands off and retries is still one record with the full cost. Full reference is in the docs.

What AgentPing tracks for OpenAI Agents SDK.

  • Cost per agent run, including hand-offs and tool calls, attributed to the customer you tag.
  • A missed-run alert when a scheduled agent stops firing.
  • Output quality on the final result, scored against your rubric.

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

Does it capture hand-offs and tool calls?
Yes. AgentPingHooks plugs into the SDK run lifecycle, so a run that hands off between agents and calls tools several times is recorded as one run with the total cost and the full trace.
Will it slow my agents down?
No. Telemetry is off the hot path with a hard 2-second timeout and a bounded queue. If AgentPing is unreachable your agent runs exactly as before.
Can I monitor a scheduled agent?
Yes. Give the agent an expected schedule and AgentPing pages you when a run does not arrive in its window, separate from the cost and quality tracking.

Monitor your OpenAI Agents SDK 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