1 item
A quiet, local-first capture layer for what you read and think while browsing. Cairn is for reading on the internet with something left over. How many times have you read a blog post that explained something perfectly, and a week later kept only the fact that you read it? The tab is closed, the title is gone, and the one paragraph you actually needed is somewhere in a search history. Cairn lets you highlight passages and write notes on any page as you browse — Wikipedia while writing an essay, papers during a literature review, docs while learning a new tool. One click, no filing, no folders. Everything lands in one archive you can browse and re-find things in later. WHAT IT DOES • Highlight anything, keep it. Select text and a small pill appears: Save keeps the passage as-is, Add note opens a box to write against it. • Save a whole page. Click the Cairn icon, then Save this page. • Write notes as you read. Press Alt+Shift+N for a side panel listing everything you've noted on this page, with a box for the next one. • Browse your archive. Open All traces from the popup: every capture grouped by page, with a site list and a filter box. • Hand context to a model. Tick the notes you want, check the size meter so you don't overload the chat, hit Copy, and paste into ChatGPT, Claude, Gemini, or whatever you use. • Or let the model fetch it. Connect Cairn's MCP server once, and Claude Code, Claude Desktop, Cursor, or any MCP client searches your notes on its own, mid-answer. • Auto-capture, if you want it. Off by default. Flip the toggle in the popup while you're on a site you read daily and Cairn saves that page's text on a timer. QUIET BY DESIGN Cairn draws one small element when you select text and gets out of the way. It never edits your captures, never sorts them for you, and never asks you to make a filing decision the moment capture asks you to think, it has failed at its job. PRIVACY Cairn saves only what you explicitly capture. It does not track your browsing history, contains no analytics or telemetry, and never sells or shares your data. Open source.
Aug 27, 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.