⇄ConnectorAgentic capabilityFree
Playwright
Cross-browser automation library for agents: control Chromium, Firefox, and WebKit with a single reliable API.
Playwright
Microsoft Playwright is the leading browser automation framework used by AI agents to navigate the web, extract data, fill forms, click buttons, and take screenshots — all with a single async API that works across Chromium, Firefox, and WebKit.
Key Features
- Multi-browser — one API for Chromium, Firefox, and WebKit (including mobile emulation)
- Auto-wait — automatically waits for elements to be actionable before interacting
- Network interception — mock, intercept, and modify HTTP requests at the browser level
- Tracing & screenshots — full trace viewer with timeline, DOM snapshots, and screenshots for every step
- Codegen — record browser interactions and export to Python, TypeScript, Java, or C#
- Headless & headed — run invisibly in CI or visibly for debugging
- MCP server — official
@playwright/mcpMCP server lets agents drive browsers via tool calls
Quick Start
pip install playwright
playwright install chromium
from playwright.sync_api import sync_playwright
with sync_playwright() as p:
browser = p.chromium.launch(headless=True)
page = browser.new_page()
page.goto("https://example.com")
print(page.title())
browser.close()
Install via ai-supply
npx ai-supply add playwright-browser-automation
Curated mirror of the open-source Playwright project (Apache-2.0). Install upstream from the repository.