Skip to main content
Control Tower gives you real-time visibility into every AI agent running in your workspace: costs, token usage, errors, and performance, without manual instrumentation. You connect your framework once, send traces via OpenTelemetry, and Orq.ai does the rest. Orq.ai Agents, Deployments, and Models used via the Orq Router, API or SDKs are monitored automatically—no additional setup required.

Get Started

This guide uses OpenAI Agents to walk you through the setup. If you are using a different framework, see Supported Agents below.
1

Get your API key

Your API key authenticates trace exports to Orq.ai. To find it:
  1. Open the Orq.ai dashboard
  2. Go to Workspace Settings → API Keys
  3. Copy an existing key or create a new one
Store it as an environment variable:
Never commit your API key to source control. Use environment variables or a secrets manager.
2

Install dependencies

3

Configure the tracer

Set up the OTLP exporter and instrument OpenAI Agents before running any code:
Python
4

Run your agent

Any OpenAI agent you run will now automatically send traces to Control Tower:
Python
Orq.ai captures: agent/Weather Assistant, tool/get_weather, model/gpt-4o.
5

Verify in Control Tower

Open the Assets page. Agents, tools, and models from your traces will appear automatically under their respective tabs.

Next Steps

Overview

Monitor all agents at a glance with summary metrics and the agents performance table.

Assets

Manage and inspect every agent, tool, deployment, and model captured in your workspace.

Supported Agents

Orq.ai Agents

Native Orq.ai Agents with automatic asset capture. Build agents in the AI Studio or via API—monitoring is built-in.

OpenAI Agents

Build agents with the OpenAI Agents SDK and automatically capture them in Control Tower via OpenTelemetry.

LangGraph

Stateful, multi-actor agent framework with graph-based orchestration. Full asset capture support.

Vercel AI

JavaScript/TypeScript SDK for AI-powered applications with streaming and multi-model support. Full asset capture support.