gemini-computer-use

Gemini 2.5 Computer Use browser automation with Playwright-based agent loops and safety confirmations. Source the env file and set your API key: Create a virtual environment and install dependencies: Run the agent script with a prompt: If both are set, COMPUTER_USE_BROWSER_EXECUTABLE takes precedence. - Implements a screenshot-to-action cycle: capture screen, send to Gemini, parse function calls, execute in Playwright, return results until task completion or turn limit - Supports multiple browser options: bundled Chromium (default), Chrome/Edge channels via COMPUTER_USE_BROWSER_CHANNEL , or custom executables like Brave - Includes safety confirmation workflow that prompts users before executing risky UI actions flagged by the model - Provides action exclusion via --exclude flag and recommends sandboxed profiles or containers for safe operation - Source the env file and set your API key: cp env.example env.sh $EDITOR env.sh source env.sh - Create a virtual environment and install dependencies: python -m venv .venv source .venv/bin/activate pip install google-genai playwright playwright install chromium - Run the agent script with a prompt: python scripts/computer_use_agent.py \ --prompt "Find the latest blog post title on example.com" \ --start-url " \ --turn-limit 6 - Default: Playwright's bundled Chromium (no env vars required). - Choose a channel (Chrome/Edge) with...