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

# SwarmZero

> Langtrace and SwarmZero Integration Guide

SwarmZero provides a platform for developers to build, deploy, and monetize AI agents. It offers an Agent Hub marketplace where developers can create and customize AI agents, while users can discover and utilize these agents for various tasks. The platform supports multiple LLM models and provides tools for creating both individual agents and swarms of collaborative agents.

## Setup

1. Install Langtrace's SDK and [initialize](/quickstart) the SDK in your code.
2. Install SwarmZero's SDK:

```bash theme={null}
pip install swarmzero
```

3. Use the `langtrace` SDK to capture traces from your SwarmZero app.

## Configuration

1. Create a `.env` file in your project directory and add your OpenAI API key:

```bash theme={null}
OPENAI_API_KEY=your-api-key-here
```

2. Create a configuration file (e.g., `swarmzero_config.toml`) for your SwarmZero agent:

```toml theme={null}
[agent]
model = "gpt-3.5-turbo"
timeout = 15
environment = "dev"
```

3. Initialize the SwarmZero agent with Langtrace:

```python theme={null}
from langtrace_python_sdk import langtrace
from swarmzero import Agent
from dotenv import load_dotenv

# Initialize Langtrace
langtrace.init(api_key=os.environ['LANGTRACE_API_KEY'])

# Load environment variables
load_dotenv()

# Create and run your agent
my_agent = Agent(
    name="my_agent",
    functions=[],
    instruction="your instructions for this agent's goal",
    config_path="./swarmzero_config.toml"
)
my_agent.run()
```

## Advanced Features

### Creating Agent Swarms

SwarmZero allows you to create swarms of collaborative agents:

```python theme={null}
from swarmzero.swarm import Swarm
from swarmzero.agent import Agent
from swarmzero.sdk_context import SDKContext

# Create individual agents
agent1 = Agent(name="Research Agent", instruction="Conduct research")
agent2 = Agent(name="Analysis Agent", instruction="Analyze data")

# Create swarm
swarm = Swarm(
    name="Research Team",
    description="Collaborative research agents",
    agents=[agent1, agent2]
)
```

### Adding Retrievers

Enable semantic search and document analysis:

```python theme={null}
my_agent = Agent(
    name="retrieve-test",
    functions=[],
    retrieve=True,
    required_exts=['.md'],
    retrieval_tool='chroma'
)
```

<img src="https://mintcdn.com/langtraceai-2/m7BVnnhK3Cx2yRxS/images/llm-frameworks/swarmzero.png?fit=max&auto=format&n=m7BVnnhK3Cx2yRxS&q=85&s=1e5ce240b35154ca641da48e1c18f028" alt="SwarmZero Interface" width="1608" height="1136" data-path="images/llm-frameworks/swarmzero.png" />

For more detailed information about SwarmZero's features and capabilities, visit their [documentation](https://docs.swarmzero.ai/sdk/agent-kit).