lobovlabs.com · Tools
3 items
Search your browser history by meaning with on-device AI. Find any page you've read, even if you forgot its title or exact words. Backtrack is AI history search that runs entirely on your device. You remember reading something, an article, a guide, a recipe, but you forgot the title, the site, even the words to search for. Chrome history only matches titles and URLs, so it comes up empty. Backtrack quietly indexes the pages you read and lets you search your browser history by meaning. Type what you remember in plain language: • "the recipe with miso and roasted eggplant" • "that article arguing rust beats go for CLI tools" • "the review comparing budget noise-cancelling headphones" Backtrack surfaces the right page, even when none of those exact words were on it. It forgives typos and loose phrasing, because it matches meaning. GOOD TO KNOW Backtrack builds its index from the moment you install it. Pages you read before installing are not in the index. It keeps your most recent 5000 articles. WHY BACKTRACK • Search by meaning. Describe what a page was about in plain words. • 100% on-device. A small AI model runs inside your browser. Your browsing never leaves your computer, and it works offline once the model is loaded. • No account, no sign-in, no cloud. Nothing to set up. • Lightweight. It indexes the readable article text and stays out of your way. • Find a site you forgot. The "tip of my tongue" problem, solved. HOW IT WORKS Every readable page you open is indexed locally a couple of seconds after it loads. The text becomes a meaning vector via an on-device AI model and is stored in your browser. When you search, your query is compared against those vectors, so the closest pages rank first.
Jul 25, 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.