Osmomark automatically highlights what matters on any page โ organizations, people, places, technical terms, and smart keywords. All runs 100% in your browser. Zero API calls. Zero data leaves your machine.
Clean underline + background highlights. No cluttered badges. Every category gets its own color โ organizations in indigo, people in green, locations in pink, keywords in orange, and entities in amber.
Three tiers of intelligence, from instant regex to full transformer NER. All running locally in your browser via WebAssembly.
URLs, emails, dates, numbers, money, and taxonomy dictionaries (programming languages, crypto, frameworks). ~60% coverage in under 5ms.
Fast POS tagging for organizations, people, places. TF-IDF keyword extraction with n-gram phrases. Verb-boosted scoring. ~85% coverage.
Full distilbert-base-NER pipeline via transformers.js. Identifies entities with ~95% accuracy. ~18MB model cached in IndexedDB. Opt-in, 5 free scans/day.
Everything runs in the page's main world โ not even a CDN fetch for the model runtime. Your text never touches a server. Period.
Upload DOCX, PDF, TXT, MD, or PPTX directly in the popup. Osmomark extracts and highlights text from documents alongside web pages.
Per-category colors, highlight styles (underline, background, border), symbol packs, and custom taxonomies. Pro unlock: full palette + exports.
Scan multiple pages at once or schedule recurring scans. Pro tracks entities across sessions with full history and entity graph visualization.
Export highlights to Readwise, Notion, and Markdown. Developer API for programmatic entity extraction. Webhook support for custom pipelines.
Share taxonomies, highlight presets, and symbol packs across your team. Admin dashboard with usage analytics and SSO support.
Chrome's Manifest V3 blocks eval() in content scripts โ which breaks most
transformer-based extensions. Osmomark works around this by injecting the model runtime
into the page's main world via a <script> tag, then bridging back
with postMessage. No eval, no CDN, no compromises.
web_accessible_resourcesTier 2b uses TF-IDF scoring with domain-aware boosting. Prioritizes verbs (3.0ร boost), extracts bigrams and trigrams (all words must be content), handles compounds ("fine-tuning", "domain-specific"), and filters ~200 NEVER_KEYWORDS including transitional adverbs, contractions, and temporal words.
No accounts. No sign-ups. No data leaving your machine. 100% local AI in your browser.
Add Osmomark to Chrome from the Web Store. It's free โ no permissions beyond what it needs.
Open any page โ article, docs, blog, PDF. Osmomark automatically scans and highlights what matters.
Named entities in color-coded highlights. Smart keywords for the gist. Deep NER for precision. Knowledge, osmotically.
Install free. 5 Deep NER scans/day included. Upgrade for unlimited access.