> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# xAI Image Agent With Memory

> Analyze an image with Grok 4.5 and retain history for follow-up questions.

The source-fidelity code uses the older `grok-2-vision-latest` model. Replace it with `grok-4.5` before running the example.

```python image_agent_with_memory.py theme={null}
"""
Xai Image Agent With Memory
===========================

Cookbook example for `xai/image_agent_with_memory.py`.
"""

from agno.agent import Agent
from agno.media import Image
from agno.models.xai import xAI
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(
    model=xAI(id="grok-2-vision-latest"),
    tools=[WebSearchTools()],
    markdown=True,
    add_history_to_context=True,
    num_history_runs=3,
)

agent.print_response(
    "Tell me about this image and give me the latest news about it.",
    images=[
        Image(
            url="https://upload.wikimedia.org/wikipedia/commons/0/0c/GoldenGateBridge-001.jpg"
        )
    ],
)

agent.print_response("Tell me where I can get more images?")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno ddgs openai
```

**2. Export your xAI API key**

```bash Mac/Linux theme={null}
export XAI_API_KEY="your_xai_api_key_here"
```

```bash Windows theme={null}
$Env:XAI_API_KEY="your_xai_api_key_here"
```

**3. Update the model**

When saving the code, replace `grok-2-vision-latest` with `grok-4.5`.

**4. Run the example**

Save the code above as `image_agent_with_memory.py`, then run:

```bash theme={null}
python image_agent_with_memory.py
```

Full source: [cookbook/90\_models/xai/image\_agent\_with\_memory.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/xai/image_agent_with_memory.py)


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