> ## Documentation Index
> Fetch the complete documentation index at: https://www.getmaxim.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# SDK HTTP Agent Quickstart

> Learn how to quickly get started with running agent evaluations via HTTP endpoints using the Maxim SDK

## How to get started with the Maxim SDK?

Get started with evaluating AI agents accessible via HTTP endpoints using the Maxim SDK. This guide will walk you through setting up the SDK and running your first agent evaluation test run.

## Installation

First, install the Maxim SDK for your preferred language:

<CodeGroup>
  ```bash Python theme={null}
  pip install maxim-py
  ```

  ```bash JS/TS theme={null}
  npm install @maximai/maxim-js
  ```
</CodeGroup>

## Getting Your API Key

Before you can use the Maxim SDK, you need to obtain an API key from the Maxim platform:

1. **Log in to Maxim**: Go to [app.getmaxim.ai/login](https://app.getmaxim.ai/login) and sign in to your account
2. **Navigate to Settings**: Click on "Settings" in the left sidebar
3. **Go to API Keys**: Click on "API keys" under "Organization settings"
4. **Generate New Key**: Click the "Generate new" button
5. **Name Your Key**: Enter a descriptive name for your API key (e.g., "Development", "CI/CD", "Local Testing")
6. **Copy the Key**: Once generated, copy the API key immediately - you won't be able to see it again

<Warning>Store your API key securely! You won't be able to view the complete key value again after closing the generation dialog.</Warning>

## Configuration

Initialize the Maxim SDK with your API key and workspace information:

<CodeGroup>
  ```python Python theme={null}
  from maxim import Maxim

  # Initialize Maxim SDK

  maxim = Maxim({"api_key": "your-api-key"})

  ```

  ```typescript JS/TS theme={null}
  import { Maxim } from '@maximai/maxim-js';

  // Initialize Maxim SDK
  const maxim = new Maxim({
    apiKey: 'your-api-key',
  });
  ```
</CodeGroup>

## Basic HTTP Agent Test Run

Here's how to create and run a basic agent evaluation test run using a workflow stored on the Maxim platform:

<CodeGroup>
  ```python Python theme={null}
  # Create a test run using a workflow

  result = (
      maxim.create_test_run(
          name="Basic Agent HTTP Evaluation", in_workspace_id="your-workspace-id"
      )
      .with_data_structure({"input": "INPUT", "expected_output": "EXPECTED_OUTPUT"})
      .with_data("your-dataset-id")
      .with_evaluators("Bias")
      .with_workflow_id("your-workflow-id")  # Your agent workflow ID on Maxim platform
      .run()
  )

  print(f"Test run completed! View results: {result.test_run_result.link}")

  ```

  ```typescript JS/TS theme={null}
  // Create a test run using a workflow
  const result = await maxim
    .createTestRun('Basic Agent HTTP Evaluation', 'your-workspace-id')
    .withDataStructure({
      Input: 'INPUT',
      'Expected Output': 'EXPECTED_OUTPUT',
    })
    .withData('your-dataset-id')
    .withEvaluators('Bias')
    .withWorkflowId('your-workflow-id') // Your agent workflow ID on Maxim platform
    .run();

  console.log(`Test run completed! View results: ${result.testRunResult.link}`);
  ```
</CodeGroup>

## Next Steps

Now that you've run your first agent evaluation, explore these guides:

* [Local Endpoint Testing](/offline-evals/via-sdk/agent-http/local-endpoint) - Test agents running on your local endpoints
* [Endpoint on Maxim](/offline-evals/via-sdk/agent-http/endpoint-on-maxim) - Use workflows stored on the Maxim platform
* [Simulation](/offline-evals/via-sdk/simulation) - Run AI-simulated multi-turn conversations
* [CI/CD Integration](/offline-evals/via-sdk/agent-http/ci-cd-integration) - Automate agent testing in your CI/CD pipeline

<Note>[Schedule a demo](https://getmaxim.ai/demo) to see how Maxim AI helps teams ship reliable agents.</Note>