jadouse5/SahhaAI

Offline, private, open-source wound-care AI for Morocco's disconnected clinics. VLM + segmentation, runs in-browser (WebGPU) or locally. By Jad Tounsi El Azzouzi. # SahhaAI — صحة AI **Offline, private, open-source wound-care AI for healthcare in disconnected zones.** Built for nurses and clinics in isolated regions of Morocco (Merzouga, the High Atlas, the deep south) where there is **no reliable internet** and **patient data must never leave the room**. > Author: **Jad Tounsi El Azzouzi** · License: Apache-2.0 · For the Moroccan AI community 🇲🇦 --- ## What it does A nurse photographs a wound or injury. SahhaAI, running **100% locally**, will: 1. **Segment** the wound region from the photo (lightweight SAM). 2. **Assess** it with a Vision-Language Model — type, severity signals, red flags. 3. **Instruct** — step-by-step first-aid in **French / Arabic / Darija / English**. 4. **Show the materials** needed — what they are, what they look like, and the **Darija word** for each (so the nurse can ask a villager for them). No cloud. No account. No data upload. Works on a plane, in the desert, in a power-cut clinic. ## Two ways to run — both offline-capable | Mode | Engine | Where | Use | |------|--------|-------|-----| | **Browser (WebGPU)** | `transformers.js` + WebGPU | Any modern laptop/phone, in a browser tab | Zero install. Scan QR → app loads → models cached → unplug internet, keep working. | | **Local (MLX)** | `mlx-vlm` | Apple Silicon Mac (M-series) | Faster, larger model, full power for the live demo. | The **same web app** is hostable on Vercel **and** runnable straight from the link as a local PWA — open it once online, it caches everything, then runs with the network off. ## Models (all small, all open) - **VLM (browser):** SmolVLM-256M-Instruct (ONNX, WebGPU) — ~150–250MB, loads on a phone; 500M variant for more quality - **VLM (local MLX):** `mlx-community/Qwen2.5-VL-3B-Instruct-4bit` — richer assessment - **Segmentation (browser):** SlimSAM (`Xenova/slimsam-77-uniform`) — WebGPU - **Segmentation (local):** LiteMedSAM — laptop-grade medical SAM - Optional upgrade: **MedGemma-4B** (Google medical VLM) for …