{"id":14155541,"url":"https://github.com/vladikoff/playwright-ai","last_synced_at":"2025-03-19T03:30:24.682Z","repository":{"id":209367958,"uuid":"723856088","full_name":"vladikoff/playwright-ai","owner":"vladikoff","description":"Command-line utility to generate LLM-based Playwright tests","archived":false,"fork":false,"pushed_at":"2023-12-08T03:29:18.000Z","size":2281,"stargazers_count":32,"open_issues_count":0,"forks_count":5,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-10-19T00:29:36.452Z","etag":null,"topics":["javascript","playwright"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vladikoff.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-26T22:56:20.000Z","updated_at":"2024-10-07T09:35:15.000Z","dependencies_parsed_at":"2024-08-17T08:16:47.323Z","dependency_job_id":null,"html_url":"https://github.com/vladikoff/playwright-ai","commit_stats":null,"previous_names":["vladikoff/playwright-ai"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vladikoff%2Fplaywright-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vladikoff%2Fplaywright-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vladikoff%2Fplaywright-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vladikoff%2Fplaywright-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vladikoff","download_url":"https://codeload.github.com/vladikoff/playwright-ai/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243960664,"owners_count":20375104,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["javascript","playwright"],"created_at":"2024-08-17T08:03:48.766Z","updated_at":"2025-03-19T03:30:24.262Z","avatar_url":"https://github.com/vladikoff.png","language":"JavaScript","funding_links":[],"categories":["javascript"],"sub_categories":[],"readme":"# playwright-ai [![](https://img.shields.io/npm/v/playwright-ai)](https://www.npmjs.com/package/playwright-ai)\n\n\n\u003e Command-line utility to generate LLM-based [Playwright](https://playwright.dev/) tests\n\n⚠️ Warning this tool is experimental and is still under development.\n\n\u003cimg src=\"assets/playwright-ai.svg\" alt=\"playwright-ai logo\" width=300 /\u003e\n\n# Usage\n\nSupported models:\n\n- Anthropic's Claude - configure API key with `ANTHROPIC_API_KEY`.\n- OpenAI's GPT3 and GPT4 - configure API key with `OPENAI_API_KEY`.\n\n## Quick start\n\n- Make sure you have the most basic Playwright installation with `npm init playwright@latest`. See https://playwright.dev/docs/intro#installing-playwright for details.\n- Install the CLI:\n\n```\nnpm -g playwright-ai\n```\n\n- Obtrain the API key for the LLM model of your choice: [Anthropic](https://www.anthropic.com) or [OpenAI](https://openai.com/).\n- Execute the CLI from project directory:\n\n```\nplaywright-ai --endpoint=https://example.com --model=claude --tests=1\n```\n\n- 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.\n\n\u003cimg src=\"assets/pw-demo.gif\" alt=\"playwright-ai demo\" /\u003e\n\n## Core Options\n\n### --endpoint (-e) :: `String`\n\n**This option is required.**\n\nThe endpoint option specifies the API endpoint to call. `playwright-ai` will browse to this endpoint and process it for generating the tests.\n\n### --model (-m) :: `String`\n\n_Default_: `gpt-4`.\n\nThe LLM model to use to generate the tests.\nAvailable options: `gpt-3`, `gpt-4`, `claude`.\n\n### --tests (-t) :: `Number`\n\n_Default_: `1`.\n\nNumber of LLM-based tests to generate.\n\n## CLI Options\n\n### --help\n\nDisplays CLI command help.\n\n### ---version\n\nShows CLI version.\n\n## Release History\n\nSee the [CHANGELOG.md](CHANGELOG.md).\n\n## TODO\n\n- Support for other models\n- More complex test cases\n\n## License\n\n[MIT](LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvladikoff%2Fplaywright-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvladikoff%2Fplaywright-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvladikoff%2Fplaywright-ai/lists"}