MLflow Typescript SDK - Anthropic

Seamlessly integrate MLflow Tracing with Anthropic to automatically trace your Claude API calls.

| Package | NPM | Description | | ----------------------- | --------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------- | | @mlflow/anthropic | | Auto-instrumentation integration for Anthropic. |

Installation

npm install @mlflow/anthropic

The package includes the @mlflow/core package and @anthropic-ai/sdk package as peer dependencies. Depending on your package manager, you may need to install these two packages separately.

Quickstart

Start MLflow Tracking Server if you don't have one already:

pip install mlflow
mlflow server --backend-store-uri sqlite:///mlruns.db --port 5000

Self-hosting MLflow server requires Python 3.10 or higher. If you don't have one, you can also use managed MLflow service for free to get started quickly.

Instantiate MLflow SDK in your application:

import * as mlflow from '@mlflow/core';

mlflow.init({
  trackingUri: 'http://localhost:5000',
  experimentId: '<experiment-id>',
});

Create a trace for Anthropic Claude:

import Anthropic from '@anthropic-ai/sdk';
import { tracedAnthropic } from '@mlflow/anthropic';

const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY });
const client = tracedAnthropic(anthropic);

const response = await client.messages.create({
  model: 'claude-3-7-sonnet-20250219',
  max_tokens: 256,
  messages: [{ role: 'user', content: 'Hello Claude' }],
});

View traces in MLflow UI:

Documentation 📘

Official documentation for MLflow Typescript SDK can be found here.

License

This project is licensed under the Apache License 2.0.