Urgent.News

What's breaking now, across thousands of outlets.

AI

Stop being your AI's eyes and hands: pwa-debug lets Claude debug your live, logged-in browser

If you've debugged a web app with an AI assistant, you know the loop: The AI asks what the console says. You copy and paste it. It asks what the component's state is. You open React DevTools and describe it. It asks you to click the button and report what happens. You click it. It asks for a screenshot. You take one. You end up as the AI's eyes and hands. That's slow, it loses information, and it…

Claude Code can now debug live, logged-in browser sessions with the help of pwa-debug. This open-source tool combines an MCP server and a browser extension, allowing the AI agent direct, structured access to crucial browser elements like the DOM, console, network, framework state, service workers, caches, and storage. By interfacing with the actual browser profile, pwa-debug provides a more accurate diagnosis of issues compared to traditional methods that rely on screenshots or OCR.

The tool covers a wide range of PWA problems, including stale caches, service worker failures, install errors, and version skew after deploys. It focuses on the specific pain points that AI assistants often struggle with, such as stale caches, service workers that won't update, and install failures. By directly interacting with the browser, pwa-debug eliminates the need for manual copying, pasting, and clicking, speeding up the debugging process and providing more accurate results.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Also reported by 1 other outlet

Read the original at dev.to →

More in AI

Anthropic's FlashProve Wants a Receipt for Every AI Answer — Explained Honestly

When you ask an AI model a question through an API, you are taking something on trust. The provider says the answer came from the model you paid for — the big, capable one, not a cheaper stand-in…

  • FlashProve provides cryptographic proof of model weights generating AI responses.
  • Prototype based on zkSNARKs verifies specific model weights for given tokens.
  • Supports Meta's Llama 4 Maverick, 400B parameters, 4-bit quantized weights.

More from Wednesday 4 November →