I built an offline-first, privacy-focused Blood Pressure tracker
Privacy-focused BP tracker without cloud—competes directly with MyFitnessPal Health and Withings Connect.

Open models + flat pricing, but ChatGPT/Claude already own privacy-conscious users.
Users concerned about data privacy, researchers, developers wanting transparent AI
Perplexity AI · HuggingChat · LocalAI
It runs only open-weight models: DeepSeek V3.2, Qwen3, Kimi K2.5, MiniMax M2.5, GLM 5. Encrypted chats, no tracking, fully deletable data.
€20/month flat, no token counting.
Available on Web, Windows, macOS, Linux, Android. iOS coming soon.
Privacy-focused BP tracker without cloud—competes directly with MyFitnessPal Health and Withings Connect.
S3-only pipeline with transparent security docs, but Zamzar and CloudConvert already do this.
Nice Jetpack Compose UI, but it's just a wrapper around Nitter.
Deterministic fingerprinting for model structure without loading weights.
C2PA inspector and true PDF redaction stand out in a sea of basic EXIF removers.
Runs full layout detection — PP-DocLayoutV3 for blocks/titles/tables and Microsoft's table-transformer for cell structure — entirely in the browser via ONNX Runtime (WASM/WebGPU), so documents never leave the tab. Impressive technical work, but the models are ~60MB and inference is CPU/GPU-heavy, so expect crashes on phones and slow analysis on older machines. The plugin-first approach (React/Svelte/Vue) and open-source repo make it a very usable proof-of-concept for privacy-first PDF tooling.