> ## Documentation Index
> Fetch the complete documentation index at: https://arizeai-433a7140.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Agent SDK (TypeScript)

> Trace Anthropic's Claude Agent SDK applications in TypeScript/Node.js with Phoenix

<Note>Looking for Python? See the [Python guide](/docs/phoenix/integrations/python/claude-agent-sdk).</Note>

[![NPM Version](https://img.shields.io/npm/v/@arizeai%2Fopeninference-instrumentation-claude-agent-sdk.svg)](https://www.npmjs.com/package/@arizeai/openinference-instrumentation-claude-agent-sdk)

This module provides [OpenInference](https://github.com/Arize-ai/openinference) instrumentation for [Anthropic's Claude Agent SDK](https://platform.claude.com/docs/en/agent-sdk/overview), automatically capturing **AGENT** and **TOOL** spans that follow OpenInference semantic conventions.

## Install

```bash theme={null}
npm install @arizeai/openinference-instrumentation-claude-agent-sdk @arizeai/phoenix-otel
```

## 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:

```typescript expandable theme={null}
import { register } from "@arizeai/phoenix-otel";
import { ClaudeAgentSDKInstrumentation } from "@arizeai/openinference-instrumentation-claude-agent-sdk";
import * as ClaudeAgentSDK from "@anthropic-ai/claude-agent-sdk";

// Initialize Phoenix tracing
const tracerProvider = register({
  projectName: "claude-agent-sdk-app",
  // If using Phoenix Cloud:
  // url: "https://app.phoenix.arize.com/s/your-space-name",
  // apiKey: process.env.PHOENIX_API_KEY,
  // If using self-hosted Phoenix:
  // url: "http://localhost:6006",
});

// Set up Claude Agent SDK instrumentation
const instrumentation = new ClaudeAgentSDKInstrumentation();
instrumentation.manuallyInstrument(ClaudeAgentSDK);

console.log("Claude Agent SDK instrumentation registered");
```

<Note>
  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()`.
</Note>

## Usage

```typescript expandable theme={null}
import "./instrumentation.js";
import { query } from "@anthropic-ai/claude-agent-sdk";

async function main() {
  for await (const message of query({
    prompt: "What is the weather in San Francisco?",
    options: {
      model: "claude-sonnet-4-5-20250514",
    },
  })) {
    if (message.type === "assistant") {
      console.log(message.content);
    }
  }
}

main();
```

## 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](https://github.com/Arize-ai/openinference), 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`:

```typescript theme={null}
const instrumentation = new ClaudeAgentSDKInstrumentation({
  traceConfig: {
    hideInputs: true, // Omit input content from spans
    hideOutputs: true, // Omit output content from spans
  },
});
instrumentation.manuallyInstrument(ClaudeAgentSDK);
```

## Resources

* [NPM Package](https://www.npmjs.com/package/@arizeai/openinference-instrumentation-claude-agent-sdk)

* [OpenInference package for Claude Agent SDK](https://github.com/Arize-ai/openinference/tree/main/js/packages/openinference-instrumentation-claude-agent-sdk)

* [Claude Agent SDK Documentation](https://platform.claude.com/docs/en/agent-sdk/overview)