Proactive AI Assistant is a Chrome extension that watches what you hover or select on the web and surfaces the most helpful AI tools in-place. It can explain code, summarize articles, graph equations, extract tables, run OCR on images, and more—all without leaving the page.
- Install dependencies
npm install
- Build the extension
npm run build
- Load in Chrome
- Open
chrome://extensions - Toggle on Developer mode
- Click “Load unpacked” and select the
distfolder
- Open
- Add your OpenAI API key
- Open the extension popup
- Switch to the Settings tab
- Save your key (stored locally via
chrome.storage)
- Hover over content or highlight text; the floating assistant suggests relevant actions.
- Results appear in the on-page window, while graphs and saved notes also sync to the side panel.
- The background service worker calls OpenAI directly from the browser, so keep your API key private.
- Run
npm run devfor webpack watch mode during UI or script changes. - Refresh the extension from
chrome://extensionsafter each build. - Logs worth checking:
chrome://extensions→ “service worker” link for background events- Browser DevTools console for content script output
src/
background/ // API calls, tool execution, state storage
content/ // DOM listeners, UI injection helpers
ui/ // React floating assistant
sidepanel/ // React side panel tabs
popup/ // Extension popup UI
utils/ // Content detectors, OCR helpers, tool metadata
manifest.json // Chrome extension manifest
webpack.config.js
- No backend: everything runs inside Chrome.
- Graphs, notes, and user settings persist via
chrome.storage.local. - New tools can be added by updating
src/utils/toolDefinitions.jsand wiring handlers insrc/background/index.js.
