nodx Lens

Highlight any text on a webpage to get an inline AI explanation. Underlines stay — click them later to revisit.

nodx Lens turns text selection into instant AI context. Highlight any phrase on any webpage, click the floating "🔍 explain" button, and a streaming explanation appears right next to what you were reading. No tab-switching, no new chat thread to clutter, no copy-pasting into another tool. ═══════════════════════════════════════════ WHO IT'S FOR ═══════════════════════════════════════════ - Anyone reading long AI replies in a chat tool — get a side-channel definition without polluting your main conversation. - Knowledge workers who skim research papers, Substack essays, technical docs, and want fast context on a term they don't know. - People who collect annotations as they read — every explanation leaves a persistent underline you can revisit. ═══════════════════════════════════════════ CORE FEATURES ═══════════════════════════════════════════ 🔍 Select-to-explain Highlight 2–500 characters on any webpage. A small "🔍 explain" pill floats above the selection. Click it. A panel slides in below the highlight with a streaming explanation — 50–150 words by default, tuned to be a quick definition with one concrete example. 📌 Persistent underlines When the explanation finishes, the selected text gets a blue underline that stays on the page. Click outside, scroll away, switch tabs — the underline doesn't disappear. Click any underline later to instantly bring the panel back with the same explanation (no extra API call). Right-click an underline to delete the annotation. 📚 Deepen on demand The panel has a "deepen" button that swaps in a longer 200–400 word explanation — mechanism, example, common misconceptions, or contrast with adjacent ideas. You decide when to spend more tokens. 🌊 Real streaming Words appear character-by-character as the model generates them. You can tell within the first sentence whether the answer is what you wanted — and close the panel early if it's off-track. No wasted wait time. ⌨️ Keyboard control Press Esc to close the panel. The trigger button auto-hides when you click elsewhere. Selection-debouncing keeps the UI from flickering as you adjust your highlight. ═══════════════════════════════════════════ PRIVACY ═══════════════════════════════════════════ This extension does not have a backend. We do not run a server. ✓ Your API key, settings, and recent explanation history live only in chrome.storage.local on your own machine. ✓ When you trigger an explanation, the request goes directly from your browser to the AI provider you configured — never through any nodx-controlled server. ✓ No analytics, no telemetry, no third-party trackers, no ads. ✓ History is capped at 20 entries, fully local, and can be cleared with one click from the toolbar popup. Full privacy policy is linked from the listing. ═══════════════════════════════════════════ HOW IT WORKS (2-MINUTE SETUP) ═══════════════════════════════════════════ 1. Install the extension. 2. Settings opens automatically on first install. 3. Pick a provider: Anthropic, OpenAI, or Google. 4. Paste your own API key (from the provider's console — you keep full control of usage and billing). 5. Pick which model to use for short vs. deep explanations. 6. Go to any webpage, highlight something, and click 🔍. ═══════════════════════════════════════════ WHY BRING-YOUR-OWN-KEY INSTEAD OF A SUBSCRIPTION ═══════════════════════════════════════════ - Privacy: your queries go to your provider account, not a middleman's. - Pay-as-you-go: a typical short explanation costs a fraction of a cent on Haiku- or Flash-class models. Light users will pay less than any flat subscription would charge. - Model freedom: swap providers or models any time. You're never locked in. - Transparency: you can see your own API console for exactly what was sent and what it cost. ═══════════════════════════════════════════ SUPPORTED MODELS ═══════════════════════════════════════════ - Anthropic — claude-haiku-4-5 (default for short explanations, fast and cheap), claude-sonnet-4-6 (default for deep explanations) - OpenAI — gpt-4o-mini, gpt-4o, gpt-5 - Google — gemini-2.5-flash, gemini-2.5-pro You can change the picked model per provider in Settings any time. ═══════════════════════════════════════════ PERMISSIONS, IN PLAIN ENGLISH ═══════════════════════════════════════════ - "Read and change all your data on all websites" — sounds scary; in practice, it's because the extension has to be ready to activate when you select text on whatever page you're reading. It does not read or modify page contents unless you explicitly click the floating trigger button. - "Storage" — to keep your API key and settings on your local machine. - "Host permissions" to api.anthropic.com, api.openai.com, generativelanguage.googleapis.com — so the extension can talk directly to whichever AI provider you chose. ═══════════════════════════════════════════ WHAT'S NEXT ═══════════════════════════════════════════ V0.1 (this release) — Core flow, persistent annotations, three providers, local history. Planned: - V0.2 — Web Crypto encryption for the stored API key - V0.3 — Global keyboard shortcut (Alt+E) to trigger without clicking - V0.4 — Annotations that survive page reload by re-anchoring to text - V0.5 — Cross-page "my annotations" library, searchable from the popup - V1.0 — Companion desktop app integration (save a snippet to deeper structured thinking) ═══════════════════════════════════════════ CONTACT / FEEDBACK ═══════════════════════════════════════════ X (Twitter): https://x.com/LaoMo9394 nodx is a small toolkit for thinking with AI as a sparring partner, not a replacement. Lens is the lightweight browser entry point. A networked decision-thinking desktop app is in development separately.