1 item
Highlight evidence sentences in research papers and PDFs from your question and concepts — private, nothing sent to the developer. Too much to read? Ask a question, and let the page answer with evidence. Agate: Academic Evidence Highlighter helps researchers and students review research papers and PDFs. Enter a research question and target concepts, and it highlights likely evidence sentences on the page, shows review cards in the side panel, labels references separately, and exports candidate results to CSV. Every result is candidate evidence for human verification — you decide what counts. You stay in control. Pause clears results and highlights while keeping your settings. Three scan modes: Scholarly (the default), All, and Manual. In Scholarly mode, only scholarly pages are read — the page-reading script is not even loaded on other pages. Unrecognized pages are not read unless you choose Scan this page once. In All mode, the extension can scan visible text on any page you choose, including personal communications displayed there. In Manual mode, nothing scans until you click Scan. Scrolling a scholarly page can scan newly loaded text as it appears. The panel speaks your language. The interface is available in English, Simplified Chinese, Japanese, and Spanish, and follows your Chrome language setting; other languages show English. Your question, concepts, and the paper's own sentences are never translated — only the extension's buttons, instructions, labels, and summary templates change language. Example prompts in the fields stay in English, because matching works on English input. Everything is processed locally on your device. Page and PDF text are not sent to the developer, and there is no account or sign-up. Your research settings and interface preferences use Chrome Storage Sync and may sync according to your Chrome settings. Built for research, but in All or Manual mode the same question-driven scanning works on any long page.
Oct 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.