Skip to main content

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.

Two non-default ways to control the Antigravity sandbox:
OptionWhen to use
Reuse by id ("env_<id>")Agent needs to build on prior work in the same sandbox (iterative project). Faster startup, state persists across runs.
Full EnvironmentConfig dictNeed a specific source repo, package set, or network policy.
The dict shape mirrors the API’s EnvironmentConfig. Only the keys you set are sent; the API applies defaults for the rest.

​
Code

cookbook/90_models/google/gemini_interactions/antigravity_environment_config.py
from agno.agent import Agent
from agno.models.google import GeminiInteractions

# Reuse an existing environment by id
agent_reuse = Agent(
    model=GeminiInteractions(
        agent="antigravity-preview-05-2026",
        environment="env_xxxxxxxx",
    ),
    markdown=True,
)

# Full EnvironmentConfig
agent_custom = Agent(
    model=GeminiInteractions(
        agent="antigravity-preview-05-2026",
        environment={
            "type": "remote",
            "sources": [
                {"type": "git", "url": "https://github.com/agno-agi/agno"},
            ],
            "network": {"allow_internet_access": True},
        },
    ),
    markdown=True,
)

if __name__ == "__main__":
    agent_reuse.print_response(
        "Continue the project we started last time and ship the next "
        "iteration of the report."
    )

    agent_custom.print_response(
        "Skim the repo we cloned, summarize the module layout, and save "
        "the summary to STRUCTURE.md inside the sandbox."
    )

​
Usage

1

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
2

Set your API key

export GOOGLE_API_KEY=xxx
3

Install dependencies

uv pip install -U "google-genai>=2.0" agno
4

Run Agent

python cookbook/90_models/google/gemini_interactions/antigravity_environment_config.py