NanoBanana

What is the NanoBanana tool?

The NanoBanana tool is a built-in capability in the Agno framework that allows AI agents to image generation via google gemini. When added to an agent in Agno Builder, the agent can autonomously decide when to invoke this tool based on the user's request.

This tool requires a GOOGLE_API_KEY environment variable. Get your API key at aistudio.google.com.

How to use NanoBanana in Agno Builder

1. 1

   Create an agent

   Drag an Agent node onto the canvas in Agno Builder, or use one of the built-in templates.

2. 2

   Enable NanoBanana

   Click the agent, go to the Tools tab, and toggle on "NanoBanana" from the ai-media category.

3. 3

   Add your API key

   Enter your GOOGLE_API_KEY in the tool configuration. Your key stays in your browser and is never stored on our servers.

4. 4

   Test in chat

   Open the chat panel and send a message. The agent will automatically use NanoBanana when relevant.

5. 5

   Export Python code

   Click File > Export Python to get clean, runnable code with the correct imports for NanoBanana.

Python code example

This is the code Agno Builder exports when you use NanoBanana:

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.nano_banana import NanoBananaTools

agent = Agent(
    name="NanoBanana Agent",
    model=OpenAIChat(id="gpt-4o"),
    tools=[NanoBananaTools()],
    instructions=["Use the nanobanana tool to help the user."],
    markdown=True,
)

agent.print_response("Help me with a nano-banana task")

Install with: pip install agno # + set GOOGLE_API_KEY