Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.openqa.io/llms.txt

Use this file to discover all available pages before exploring further.

​
Playwright Integration

Add OpenQA to your existing Playwright project.

​
Installation

npm install openqa

​
Authentication

claude login

​
Usage

import { test, expect } from "@playwright/test";
import { runAgent } from "openqa";

test("AI fills and submits form", async ({ page, context }) => {
  await page.goto("https://example.com/form");

  // AI agent uses same browser context
  await runAgent("Fill in the form with test data", context);

  // Continue with standard assertions
  await expect(page.locator('input[name="email"]')).toHaveValue("test@example.com");
});

​
How Context Sharing Works

OpenQA uses @playwright/mcp to share the browser context between your test and the AI agent:
  • Shared cookies and session storage
  • Same page state and navigation history
  • True collaborative automation
test("Multi-step flow", async ({ context }) => {
  // Agent navigates and logs in
  await runAgent("Go to app.example.com and log in as test@example.com", context);
  
  // Agent continues in same session
  await runAgent("Navigate to settings and enable dark mode", context);
  
  // Your test can verify the result
  const page = context.pages()[0];
  await expect(page.locator("body")).toHaveClass(/dark/);
});

​
Options

Pass configuration as the third argument: 
await runAgent("Click submit", context, {
  verbose: false,        // Disable logging
  agentType: "langchain" // Use LangChain instead of Claude
});
See API Reference for all options.