Show HN: Libretto PR agents – Automatically fix failing playwright scripts
Libretto has introduced a new tool for Playwright users that automatically investigates failed browser automation scripts. When a test fails, the agent analyzes the live page and generates a GitHub pull request with a proposed code fix.
Why it matters
This tool aims to reduce the maintenance burden for software engineers by automating the debugging process for web automation testing.
Docs Blog Changelog Sign in/up // PLAYWRIGHT PR AGENTS -- Automatically fix failing Playwright scripts 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.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in