c4634d4965
Encrypt (Options) and decrypt (background) now share one module; wire format unchanged. Tests include fixtures proving values encrypted by the old inline Options code still decrypt, plus tamper/wrong-key cases. The module documents the honest threat model (key co-located with ciphertext = obfuscation, not encryption). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
⚡ LexAI — AI Writing Assistant
A Grammarly-like Chrome Extension powered by your own LLM API key. No monthly subscription. Full control.
Features (Roadmap)
- ✅ Grammar & spelling correction
- ✅ Rephrase / rewrite text
- ✅ Shorten or expand text
- 🔜 Tone suggestions
- 🔜 Autocomplete
- 🔜 Custom style profiles
Supported LLM Providers
- OpenAI (GPT-4o, GPT-4o-mini)
- Anthropic (Claude 3.5 Haiku, Sonnet)
- Groq (free tier — fast!)
- OpenRouter (100+ models)
Tech Stack
- WXT + React 18 + TypeScript
- Manifest V3
- Inline-styled UI (no CSS framework)
Development
npm install
npm run dev # Dev mode with hot reload
npm run build # Production build
npm run zip # Package for Chrome Web Store
npm test # Run unit tests
Load in Chrome
- Run
npm run build - Open Chrome →
chrome://extensions - Enable Developer Mode
- Click Load unpacked → select
.output/chrome-mv3
Project Management
Plane: LEXAI project → https://plane-pro.juankibin.space