agent-screenshot

[](https://github.com/rodbland2021/agent-screenshot/actions/workflows/ci.yml) [](LICENSE) [](CHANGELOG.md)

Two tools for giving AI agents eyes. Automated web screenshots with Vision-optimised tiling, plus desktop screen capture.

# Screenshot a web page (tiled for Claude Vision)
python screenshot.py https://example.com --full-page

# Capture your desktop screen
python grab.py

| Tool | What it does | |------|-------------| | screenshot.py | Playwright-based web screenshots. Full-page captures are automatically tiled into 1072x1072 chunks optimised for Claude Vision and other multimodal models. | | grab.py | Desktop screen capture using Python's mss library. 14 region presets (halves, thirds, quadrants) for targeting specific parts of your display. |

git clone https://github.com/rodbland2021/agent-screenshot.git
cd agent-screenshot
pip install -r requirements.txt
playwright install chromium

Verify it works:

python screenshot.py https://example.com
# Should print a file path like /tmp/screenshots/example-com_1234567890.jpg

Takes automated screenshots of any URL using headless Chromium.

# Basic screenshot
python screenshot.py https://example.com

# Mobile viewport (375x812)
python screenshot.py https://example.com --mobile

# Full page, tiled for AI Vision models
python screenshot.py https://example.com --full-page

# Dismiss cookie banners and popups
python screenshot.py https://example.com --dismiss-popups --wait-until load --wait 3000

# Custom auth header
python screenshot.py https://internal-app.com --header "Authorization=Bearer mytoken"

# Screenshot a specific element
python screenshot.py https://example.com --selecto