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

# Installation

> Step-by-step installation instructions for different environments

## Overview

This guide covers the installation of Julep in various environments and configurations.

### Prerequisites

Before installing Julep, ensure you have:

* Python 3.8+ or Node.js 16+ installed
* pip (for Python) or npm/bun (for Node.js) package manager
* A Julep API key ([Get one here](https://dashboard.julep.ai))

### Package Installation

> [tab] Python
>
> 1. Using pip:
>
> ```bash theme={"dark"}
> pip install julep
> ```
>
> 2. Using poetry:
>
> ```bash theme={"dark"}
> poetry add julep
> ```
>
> 3. Using pipenv:
>
> ```bash theme={"dark"}
> pipenv install julep
> ```

> [tab] Node.js
>
> 1. Using npm:
>
> ```bash theme={"dark"}
> npm install @julep/sdk
> ```
>
> 2. Using yarn:
>
> ```bash theme={"dark"}
> yarn add @julep/sdk
> ```
>
> 3. Using bun:
>
> ```bash theme={"dark"}
> bun add @julep/sdk
> ```

### Environment Setup

#### Setting up Environment Variables

It's recommended to use environment variables for sensitive information like API keys:

1. Create a `.env` file in your project root:

```bash theme={"dark"}
JULEP_API_KEY=your_api_key_here
JULEP_ENVIRONMENT=production  # or dev (development)
```

2. Load the environment variables in your code:

```python Python theme={"dark"}
import os
from dotenv import load_dotenv
from julep import Julep

load_dotenv()

client = Julep(
    api_key=os.getenv('JULEP_API_KEY'),
    environment=os.getenv('JULEP_ENVIRONMENT', 'production')
)
```

```javascript Node.js theme={"dark"}
import dotenv from 'dotenv';
import { Julep } from '@julep/sdk';

dotenv.config();

const client = new Julep({
  apiKey: process.env.JULEP_API_KEY,
  environment: process.env.JULEP_ENVIRONMENT || 'production'
});
```

### Verification

To verify your installation:

```python Python theme={"dark"}
from julep import Julep
import os
from dotenv import load_dotenv

load_dotenv()

client = Julep(
    api_key=os.getenv('JULEP_API_KEY'),
    environment=os.getenv('JULEP_ENVIRONMENT', 'production')
)

# Test connection
agent = client.agents.create(
    name="Test Agent",
    model="claude-3.5-haiku",
    about="A test agent"
)
print(f"Successfully created agent: {agent.id}")
```

```javascript Node.js theme={"dark"}
import { Julep } from '@julep/sdk';
import dotenv from 'dotenv';

dotenv.config();

const client = new Julep({
  apiKey: process.env.JULEP_API_KEY,
  environment: process.env.JULEP_ENVIRONMENT || 'production'
});

// Test connection
const agent = await client.agents.create({
  name: "Test Agent",
  model: "claude-3.5-haiku",
  about: "A test agent"
});
console.log(`Successfully created agent: ${agent.id}`);
```

### IDE Integration

Enhance your development experience by accessing Julep documentation directly in your IDE through the [Context7 MCP server](https://context7.com/julep-ai/julep). This integration allows you to:

* Access Julep documentation without leaving your IDE
* Get instant answers about Julep APIs and concepts
* View code examples and best practices inline

To set up the integration, visit [Context7 Julep Documentation](https://context7.com/julep-ai/julep) and follow the instructions for your specific IDE.

### Troubleshooting

Common installation issues and solutions:

1. **API Key Issues**
   * Ensure your API key is valid and properly set in environment variables
   * Check if you're using the correct environment (production/development)

2. **Version Compatibility**
   * Make sure you're using compatible versions of Python/Node.js
   * Update to the latest SDK version if you encounter issues

3. **Docker Issues**
   * Verify Docker is running and has sufficient resources
   * Check if required ports are available and not blocked

### Next Steps

Now that you have Julep installed, you can:

> [card] [Quick Start](https://docs.julep.ai/introduction/quickstart.md)
>
> Create your first Julep agent and task


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.