4 items
Turns console errors and failed requests into a ranked, plain-English digest, one-click markdown export for AI. 100% local. bug-digest watches the console and network for the page you're testing and turns the noise into a short, ranked, plain-English list of what's actually broken, entirely on your machine. The problem with devtools isn't missing information, it's noise. A hundred console lines show up and three of them matter. bug-digest deterministically finds the three, explains them in plain English, collapses the other ninety-seven into an inspectable "ignorable" count, and formats the result for pasting straight into Claude, ChatGPT, or any AI assistant. WHAT IT DOES • Watches console.error/warn, uncaught exceptions, unhandled promise rejections, and failed network requests on the page you're viewing • Deduplicates repeated messages into one entry with a count • Ranks by severity, uncaught exceptions and same-origin failures first, so the worst problem leads • Groups related events (e.g. a failed request and the console error it caused) into one incident instead of two unrelated rows • Matches common problems (server not running, CORS, 401/403, React hydration mismatches, missing keys, and more) against a plain-English rules table with fixes • One-click "Copy for AI" exports the full technical digest as clean markdown • A toolbar badge shows the current tab's open-problem count at a glance WHY IT'S DIFFERENT Zero LLM calls. Zero network requests of any kind. Zero accounts. Zero analytics. Everything (deduplication, ranking, correlation, rule matching, the markdown export) runs as pure, open-source, unit-tested code in your browser. The only place AI enters the picture is whatever tool you paste the markdown into, which is entirely up to you. WHO IT'S FOR Built especially for people who are still learning to read devtools, and for anyone whose debugging loop is "copy the error, ask an AI." It's just as useful for experienced developers who want the full technical detail (stack traces, request info, event timelines) one click away. OPEN SOURCE MIT licensed. Source, rules table, and contribution guide: https://github.com/anveshasaraf/bug-digest
Jul 29, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.