Gemini Computer Use

Quick start

1. Source the env file and set your API key:

``bash cp env.example env.sh $EDITOR env.sh source env.sh ``

1. Create a virtual environment and install dependencies:

``bash python -m venv .venv source .venv/bin/activate pip install google-genai playwright playwright install chromium ``

1. Run the agent script with a prompt:

``bash python scripts/computeruseagent.py \ --prompt "Find the latest blog post title on example.com" \ --start-url "https://example.com"; \ --turn-limit 6 ``

Browser selection

• Default: Playwright's bundled Chromium (no env vars required).
• Choose a channel (Chrome/Edge) with COMPUTERUSEBROWSER_CHANNEL.
• Use a custom Chromium-based executable (e.g., Brave) with COMPUTERUSEBROWSER_EXECUTABLE.

If both are set, COMPUTERUSEBROWSER_EXECUTABLE takes precedence.

Core workflow (agent loop)

1. Capture a screenshot and send the user goal + screenshot to the model.
2. Parse function_call actions in the response.
3. Execute each action in Playwright.
4. If a safetydecision is requireconfirmation, prompt the user before executing.
5. Send function_response objects containing the latest URL + screenshot.
6. Repeat until the model returns only text (no actions) or you hit the turn limit.

Operational guidance

• Run in a sandboxed browser profile or container.
• Use --exclude to block risky actions you do not want the model to take.
• Keep the viewport at 1440x900 unless you have a reason to change it.

Resources

• Script: scripts/computeruseagent.py
• Reference notes: references/google-computer-use.md
• Env template: env.example