Skip to main content
Looking for Python? See the Python guide.
NPM Version This module provides OpenInference instrumentation for Anthropic’s Claude Agent SDK, automatically capturing AGENT and TOOL spans that follow OpenInference semantic conventions.

Install

Setup

To instrument your Claude Agent SDK application, use the register function from @arizeai/phoenix-otel and set up the Claude Agent SDK instrumentation. Create the instrumentation.ts file:
The Claude Agent SDK is ESM-only, so manuallyInstrument() is used instead of enable() to ensure compatibility. You must import the SDK namespace and pass it to manuallyInstrument().

Usage

Observe

With instrumentation enabled, you will see the following in Phoenix:
  • AGENT spans wrapping the full query() call, capturing the prompt and final response
  • TOOL spans for each tool invocation made by the agent during execution
These spans follow OpenInference semantic conventions, making them fully compatible with Phoenix’s trace visualization and evaluation features.

Privacy Configuration

You can configure the instrumentation to hide sensitive data using traceConfig:

Resources