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

# Image Agent with Memory

> Give a Together vision agent conversation history to answer follow-up questions about a prior image.

## Code

```python image_agent_with_memory.py theme={null}
import os

from agno.agent import Agent
from agno.media import Image
from agno.models.together import Together

agent = Agent(
    model=Together(id=os.environ["TOGETHER_MODEL_ID"]),
    markdown=True,
    add_history_to_context=True,
    num_history_runs=3,
)

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

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

Set `TOGETHER_MODEL_ID` to a current model that accepts image input. See the [Together vision guide](https://docs.together.ai/docs/inference/vision/overview) and [serverless catalog](https://docs.together.ai/docs/serverless/models).

## Usage

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

  <Step title="Set your API key">
    ```bash theme={null}
    export TOGETHER_API_KEY=xxx
    export TOGETHER_MODEL_ID=your-model-id
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U openai agno
    ```
  </Step>

  <Step title="Run Agent">
    Save the code above as `image_agent_with_memory.py`, then run:

    ```bash theme={null}
    python image_agent_with_memory.py
    ```
  </Step>
</Steps>