> ## 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.

# Maxim Integration for Agno

> Integrate Maxim with your Agno Agents for Observability

## Getting Started

### Prerequisites

* Python version >=3.10
* A Maxim account ([sign up here](https://getmaxim.ai/))
* Generate Maxim API Key
* An Agno project

### Installation

Install the Maxim SDK via pip:

```python theme={null}
pip install maxim-py
```

Or add it to your `requirements.txt`:

### Basic Setup

### 1. Set up environment variables

```env theme={null}
### Environment Variables Setup

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

# Maxim API Configuration
MAXIM_API_KEY=your_api_key_here
MAXIM_LOG_REPO_ID=your_repo_id_here
OPENAI_API_KEY=your_openai_api_key
# You can also choose another LLM Provider (Gemini, Groq, Anthropic etc.)
```

### 2. Import the required packages

```python theme={null}
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.googlesearch import GoogleSearchTools
from agno.tools.yfinance import YFinanceTools
from maxim import Maxim
from maxim.logger.agno import instrument_agno
```

### 3. Initialise Maxim with your API key

```python {8} theme={null}
# Instrument Agno with just one line
instrument_agno(Maxim().logger())
```

### 4. Create and run your Agno application as usual

```python theme={null}
# Create your agent
researcher = Agent(
    name="Research Agent",
    role="Senior Research Analyst",
    model=OpenAIChat(id="gpt-4o"),
    tools=[GoogleSearchTools()],
    instructions="You are an expert researcher at a tech think tank...",
    show_tool_calls=True,
    markdown=True
)

# Run your agent
response = researcher.run("Research the latest AI advancements...")
print(response.content)
```

That's it! All your Agno agent interactions will now be logged and available in your Maxim dashboard.

Check this Cookbook for a quick reference - [Notebook](https://github.com/maximhq/maxim-cookbooks/blob/main/python/observability-online-eval/agno/agent.ipynb)

## Multi-Agent Example

Here's how to set up a multi-agent system with Maxim integration:

```python theme={null}
# Create individual agents
web_search_agent = Agent(
    name="Web Agent",
    role="Search the web for information",
    model=OpenAIChat(id="gpt-4o"),
    tools=[GoogleSearchTools()],
    instructions="Always include sources",
    show_tool_calls=True,
    markdown=True,
)

finance_agent = Agent(
    name="Finance Agent",
    role="Get financial data",
    model=OpenAIChat(id="gpt-4o"),
    tools=[YFinanceTools(stock_price=True, analyst_recommendations=True, company_info=True)],
    instructions="Use tables to display data",
    markdown=True,
)

# Create multi-agent system
multi_ai_agent = Agent(
    team=[web_search_agent, finance_agent],
    model=OpenAIChat(id="gpt-4o"),
    instructions="You are a helpful financial assistant. Answer user questions about stocks, companies, and financial data.",
    show_tool_calls=True,
    markdown=True
)

# Run the multi-agent system
response = multi_ai_agent.run("What's the current stock price of Apple?")
print(response.content)
```

## Viewing Your Traces

After running your Agno application:

1. Log in to your [Maxim Dashboard](https://app.getmaxim.ai/login)
2. Navigate to your repository
3. View detailed agent traces, including:
   * Agent conversations
   * Tool usage patterns
   * Performance metrics
   * Cost analytics
   * Token usage
   * Model information

<img src="https://mintcdn.com/maximai/ieTtaXix416w-43r/images/agno.gif?s=348963b90632d713933c9bcfded51908" alt="agno.gif" width="1280" height="720" data-path="images/agno.gif" />

## Troubleshooting

### Common Issues

* **No traces appearing**: Ensure your API key and repository ID are correct
* Ensure you've **`called instrument_agno()`** ***before*** running your agents. This initializes logging hooks correctly.
* Set `debug=True` in your `instrument_agno()` call to surface any internal errors:

  ```python theme={null}
  instrument_agno(logger, {"debug" : True})
  ```
* Double-check that `instrument_agno()` is called **before** creating or executing agents. This might be obvious, but it's a common oversight.

### Debug Mode

Enable debug mode to see detailed logging information:

```python theme={null}
from maxim import Maxim
from maxim.logger.agno import instrument_agno

# Enable debug mode
maxim = Maxim()
instrument_agno(maxim.logger(), {"debug":True})
```

## Resources

<CardGroup cols="3">
  <Card title="Agno Docs" icon="book" href="https://github.com/agno-agi/agno">
    Official Agno documentation
  </Card>

  <Card title="Maxim Docs" icon="book" href="https://getmaxim.ai/docs">
    Official Maxim documentation
  </Card>

  <Card title="Maxim Github" icon="github" href="https://github.com/maximhq">
    Official Maxim GitHub repository
  </Card>
</CardGroup>