Repository files navigation

Command-line utility to generate LLM-basedPlaywright tests

⚠️ Warning this tool is experimental and is still under development.

Supported models:

• Anthropic's Claude - configure API key withANTHROPIC_API_KEY.
• OpenAI's GPT3 and GPT4 - configure API key withOPENAI_API_KEY.

• Make sure you have the most basic Playwright installation withnpm init playwright@latest. Seehttps://playwright.dev/docs/intro#installing-playwright for details.
• Install the CLI:

npm -g playwright-ai

• Obtrain the API key for the LLM model of your choice:Anthropic orOpenAI.
• Execute the CLI from project directory:

playwright-ai --endpoint=https://example.com --model=claude --tests=1

• After the CLI is done, it will generate the tests into the Playwright test directory. As the tests generate, the CLI will have both passing and failing tests. The failing tests will have to be manually fixed by the user of the tool.

This option is required.

The endpoint option specifies the API endpoint to call.playwright-ai will browse to this endpoint and process it for generating the tests.

Default:gpt-4.

The LLM model to use to generate the tests.Available options:gpt-3,gpt-4,claude.

Default:1.

Number of LLM-based tests to generate.

Displays CLI command help.

Shows CLI version.

See theCHANGELOG.md.

• Support for other models
• More complex test cases

MIT