I built a background remover that doesn't upload your photos (no $40/month) A developer built Cutout, an AI background remover that runs entirely in the browser using WebAssembly and WebGPU, ensuring no photos are uploaded to any server. The tool offers instant removal, batch mode, background replacement, and manual refinement, all without requiring a subscription or sign-up. Remove.bg is a great tool, but it has a problem: they upload your photos to their servers. For personal photos, product images, or sensitive pictures, that's not ideal. So I built Cutout — an AI background remover that runs entirely in your browser. No backend, no uploads, no sign-up, no $40/month subscription. Try it: https://cutout-murex.vercel.app https://cutout-murex.vercel.app Source: https://github.com/JeffreyHamilton6399/Cutout https://github.com/JeffreyHamilton6399/Cutout How it works The app uses @imgly https://dev.to/imgly /background-removal, a powerful AI library that runs directly in the browser via WebAssembly. When you drop an image: The AI model downloads one-time, ~40MB, then cached by the browser The model runs locally via WebGPU/WASM to segment the foreground The background is removed, leaving a transparent PNG You download the result Your photo literally never leaves your device. There is no server. Features Instant removal: Drop a photo, get a transparent PNG in seconds. Batch mode: Remove backgrounds from multiple images at once. Background replacement: Keep it transparent, or add a solid white/black background for JPEG export. Manual refine: If the AI isn't perfect, use the eraser/restore brush to clean up edges. The privacy model 100% client-side — photos are processed in your browser Zero network requests during processing except the one-time model download No accounts, no tracking, no analytics No server-side storage — there IS no server Open source — read every line of code Try it Live: https://cutout-murex.vercel.app https://cutout-murex.vercel.app Source: https://github.com/JeffreyHamilton6399/Cutout https://github.com/JeffreyHamilton6399/Cutout Feedback welcome — happy to answer questions about the WASM model or the architecture.