WildLens: an offline field notebook that tells you what you just found outside

Description and use

WildLens is a mobile‑first, offline‑first PWA that identifies plants, birds, animals, and insects using the open‑weight BioCLIP model, provides honest uncertainty, safety notes, and a local field journal.

Problem

Users want to identify plants, birds, animals or insects while outdoors without relying on internet or uploading photos.

Outcome

WildLens enables quick, privacy‑preserving identification of living subjects outdoors, with honest uncertainty and a notebook‑style journal.

Workflow

• Open the PWA in the phone browser
• Allow camera access
• Take a photo of a living subject
• The model runs in the browser and returns top‑3 guesses or a no‑subject result
• Optional: add notes and approximate location to the local journal
• Export or clear the journal as desired

Evidence

WildLens is a small field notebook that lives in your phone's browser. Point the camera at a plant, bird, animal or insect and it tells you what it thinks you're looking at.

Source

The identification runs entirely on your device, so your photos are never uploaded, and once the model has downloaded the app is built to keep working with no signal.

Source

The model file is far too big for GitHub, so it lives in a Hugging Face model repo. The app downloads it once and keeps it in the browser cache.

Source

I exported its image encoder to ONNX once, in Google Colab, and the app runs it in the browser with ONNX Runtime Web (WebAssembly).

Source

The app works best on a phone. Open it, allow camera access, and on first launch let it download the model (about 330 MB) over Wi‑Fi. That's a one‑time download, and the model is kept in your browser's cache afterwards.

Source