An AI-powered browser extension that spots logical gaps and reasoning issues in articles.
# Install dependencies
npm install
# Set up environment
cp .env.example .env
# Edit .env - defaults work for local Postgres via Docker
# Start local Postgres
npm run dev:db
# Run migrations
npx prisma migrate deploy
# Start development server (watches for changes)
npm run devThe app works without ANTHROPIC_API_KEY - only the /analyze endpoint requires it.
- Run
npm run buildto build the extension - Navigate to
chrome://extensionsin Chrome/Edge - Enable "Developer mode"
- Click "Load unpacked" and select the
build/extension/folder - Click the extension icon on any article
npm run dev # Build + start server + watch for changes
npm run dev:db # Start local Postgres (Docker)
npm run dev:db:stop # Stop local Postgres
npm run build # Full production build
npm run typecheck # TypeScript type checking
npm test # Run tests (unit tests with mocks)
npm run lint # ESLint
npm run pipeline # Test analysis pipelines: npm run pipeline <name> <articles-dir>
# Integration testing (requires ANTHROPIC_API_KEY in .env)
VITEST_INTEGRATION=true npm test # Run tests against real APIThe backend is designed for Railway deployment:
- Create a new project on Railway
- Add a PostgreSQL database
- Connect this GitHub repo
- Set
ADMIN_KEYenvironment variable for admin access - Deploy — Railway will automatically:
- Install dependencies
- Bundle the extension for download
- Run database migrations
- Start the server
Note: Ensure "Root Directory" is blank (deploys from repo root).