About
What is auto-playwright?
auto-playwright is an open-source library designed to automate Playwright test steps using ChatGPT. It enables developers to write tests using plain-text instructions, eliminating the need for precise selectors and reducing the strong coupling with application markup often found in conventional testing. This approach facilitates rapid test creation and allows for a Test-Driven Development (TDD) workflow, where tests can be written concurrently with or even before functionality development. The tool supports various Playwright actions like clicking, filling, querying data, and asserting states, and can be configured with OpenAI or Azure OpenAI. While free to use, it incurs costs associated with OpenAI API usage, estimated at around $0.01 per test step with GPT-4 Turbo.
Best used for
Ideal for developers who need to automate web testing, accelerate test creation, and simplify test maintenance. Especially valuable for those looking to reduce reliance on specific UI selectors and adopt a more natural language approach to test automation.
Common actions
github copilotface swapping"AI Agents"automated workflowworkflowsopen-sourcedeepfakelow-code/no-codecollaboration
Capabilities
Key features
- AI-driven Playwright automation
- Plain-text test instructions
- HTML sanitization
- OpenAI API integration
- Azure OpenAI support
- Supports Playwright actions
- Debug mode
Integrations
openaiazure-openai
Pricing & Plans
Open Source ยท Usage-based
FAQs
What are the costs associated with using auto-playwright?
While auto-playwright itself is free and open-source, it relies on the OpenAI API, which incurs usage-based costs. For example, a single test step using GPT-4 Turbo is estimated to cost approximately $0.01. The actual price can vary depending on the payload size and the specific OpenAI model used.
How does auto-playwright compare to ZeroStep?
auto-playwright is inspired by ZeroStep and offers a similar API, but ZeroStep provides a more robust implementation with a proprietary backend. auto-playwright is open-source and uses the OpenAI API directly, while ZeroStep uses its own backend and offers features like screenshots, parallelism, and WebSockets not present in auto-playwright.
Can auto-playwright be used with Azure OpenAI?
Yes, auto-playwright supports integration with Azure OpenAI. You need to provide specific configuration options including the API key, resource name, model deployment name, base URL, and API version to connect to your Azure OpenAI instance for automating Playwright steps.