Skip to main content
Stream the Antigravity agent’s progress (tool calls, intermediate text, generated artifacts) instead of waiting for the final result. Antigravity runs in the foreground, so the stream stays open for the duration of the autonomous loop. No background reconnect is needed.

​
Code

cookbook/90_models/google/gemini_interactions/antigravity_streaming.py
import asyncio

from agno.agent import Agent
from agno.models.google import GeminiInteractions

agent = Agent(
    model=GeminiInteractions(
        agent="antigravity-preview-05-2026",
        environment="remote",
    ),
    markdown=True,
)

if __name__ == "__main__":
    agent.print_response(
        "Read Hacker News, summarize the top 5 stories, and save the "
        "summary as a Markdown report.",
        stream=True,
    )

    asyncio.run(
        agent.aprint_response(
            "Find the three most-starred new Python repos on GitHub this "
            "week and write a one-paragraph blurb for each.",
            stream=True,
        )
    )

​
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_streaming.py