Keep the browser automations you already run. When one fails, Libretto investigates the live page and opens a GitHub pull request with a proposed code fix.
The sign-in field is name="login", confirmed by inspecting the live page.
Your existing Playwright script runs normally. The PR agent starts only after a failure, when it can investigate what changed and propose a fix.
Add Libretto at the failure boundary without changing your fixtures, retries, logging, or deployment.
Run locally, in your own infrastructure, or with a hosted browser provider. The agent uses the live page you already created.
Choose your LLM provider and keep its API key in your own environment.
Libretto does not charge for the PR agent. Your model and browser providers may still charge for their usage.
The PR agent focuses on diagnosing the failure and proposing a code fix for future runs. Your existing catch, retry, fallback, and error handling remain responsible for the current run, while the agent opens a pull request when it finds a fix.
No. Add libretto-playwright-debugger to an existing Playwright project, initialize the debugger once, and call debugFailure() from the failure path. Your current runtime, browser provider, deployment, and workflow structure stay in place.
Not yet. The current package accepts a Playwright Page, so the failed automation must run through Playwright. Selenium and Puppeteer would require separate adapters.
Yes. The PR agent works with local, self-hosted, and hosted browsers as long as your automation has a live Playwright Page and keeps it open while debugFailure() runs. You do not need to use Libretto Cloud for the browser session.
Libretto does not charge for the PR agent. You bring your own model provider API key and browser infrastructure, so your model or browser provider may still charge for their usage.
Yes. The Playwright debugger package is open source under the MIT license in the Libretto repository.