Private photo search

Find any photo by describing it.

Search your entire library in plain language — plus faces, places, moods and the text inside documents. Every AI model runs on your own machine. Nothing is uploaded, ever.

Windows 10 / 11 · macOS coming soon · 3-day free trial, no account needed

No cloud upload No account for search Works fully offline Indexes photos anywhere on disk
What it does

One search box for everything in your photos

BoxPick builds a private, on-device index of your library so you can find things the way you actually remember them.

🔍

Natural-language search

“red bicycle against a brick wall”, “birthday cake with candles”. Semantic matching with a local CLIP model — no tags to maintain.

🧬

Duplicate finder

Four tiers — identical files, re-saved or resized copies, the same shutter press across RAW/JPEG/HEIC, and near-identical burst frames — each with a suggested keeper and a “reclaim X GB” estimate.

👤

People

Faces detected and clustered on-device. Name someone once and every photo of them is grouped.

📍

Places

GPS photos are reverse-geocoded offline — browse by city or region with no map service.

🎭

Moods

Calm, festive, dramatic, cozy… a zero-shot classifier sorts your library by feel.

📄

Document text

On-device OCR reads receipts, screenshots, whiteboards and slides. Search the words inside the picture.

📅

On This Day

Resurfaces photos taken on today’s date in earlier years, entirely from your local index.

🗂️

Collections

Hand-made albums alongside the automatic groupings — the only things in the app you can delete, by design.

Resumable indexing, optional GPU

Close the app mid-scan and it picks up exactly where it left off — the queue is on disk. DirectML acceleration kicks in automatically on supported hardware; everything still works on CPU alone.

How it works

Three steps, then it just works

Point it at your photos

Pick any folders on your drives. BoxPick never moves, edits or deletes your originals.

It indexes on your device

Embeddings, faces, places, moods and OCR are computed locally and stored in a single database on your machine.

Search instantly, forever offline

Once indexed, every search is local and immediate — on a plane, in a bunker, with the Wi-Fi off.

System requirements

What you need to run it

BoxPick runs on ordinary hardware. A faster CPU and more RAM mainly speed up the one-time indexing pass — day-to-day search is light.

Minimum

OS
Windows 10 or 11, 64-bit
CPU
Any 64-bit dual-core (x64)
RAM
8 GB
Disk
2 GB for the app + AI models, plus ~1–2 GB per 100k photos indexed
GPU
Not required — runs on CPU
Internet
First launch only (≈580 MB model download) + an occasional licensing check

Recommended Best experience

OS
Windows 11, 64-bit
CPU
Modern quad-core or better (Intel 8th-gen / Ryzen 3000 and up)
RAM
16 GB
Disk
SSD with 10 GB+ free (large libraries index noticeably faster)
GPU
Any DirectX 12 GPU — DirectML accelerates search and mood tagging
Internet
Same — the app is fully offline after setup

Supported formats today: JPEG, PNG, HEIC/HEIF, TIFF, WebP. RAW support is planned. macOS build is in progress.

Privacy

Your photos never leave your computer

This isn’t a policy promise layered over a cloud service — there is no server for your photos to go to. The models run on your CPU or GPU.

The one exception: licensing. To check whether your free trial or subscription is active, the app makes an occasional call that sends only a hashed device ID and — once you subscribe — your email address. Never anything about your photos.

Pricing

Free for 3 days, then a simple subscription

Monthly

$4.99 / month

Cancel anytime.

  • Unlimited on-device search & indexing
  • All features, all updates
  • One person, your own devices

Annual

$44.99 / year

Two months free vs. monthly.

  • Everything in Monthly
  • Best value

What happens when the trial ends? Starting a new search or indexing a new folder asks you to subscribe. Everything already indexed — browsing your people, places, moods, documents, collections, duplicates and On This Day — stays fully usable. Nothing you’ve built is ever locked away. Regional pricing (₹ for India) is shown automatically at checkout.

Download

Get BoxPick for your computer

Install, point it at a folder, and start searching. The 3-day trial begins on first launch.

Download for Windows macOS — coming soon

Windows 10 or 11, 64-bit · ~250 MB installer · first launch downloads ~580 MB of AI models (one time, then fully offline). The app updates itself — new versions install on the next restart.

BoxPick isn’t code-signed yet, so Windows may show a “Windows protected your PC” prompt — click More info → Run anyway. This goes away as more people install.

FAQ

Questions people ask first

Do my photos get uploaded anywhere?

No. All indexing and search happens on your machine. The only network traffic the app ever makes is the licensing check, which sends a hashed device ID and (after you subscribe) your email — nothing about your photos.

Does it work without internet?

Yes, completely — for indexing and every kind of search. The licensing check has an offline grace period, so a flight or an outage won’t lock you out.

What AI models does it use?

A CLIP vision–language model for semantic search and moods, a compact face detector/recognizer for people, and an on-device OCR engine for document text. They’re bundled with the app and run via ONNX Runtime on CPU, with optional GPU acceleration.

Will it modify or delete my photos?

Never automatically. It only reads your files. The duplicate finder’s “move to Recycle Bin” is the single action that touches a file, it’s always your explicit click, and it’s reversible from the Recycle Bin.

Does it support RAW files?

Not yet — JPEG, PNG, HEIC/HEIF, TIFF and WebP today. RAW support is planned; the duplicate finder is already built to pair a RAW with its out-of-camera JPEG once RAW decoding lands.

How long is the free trial?

3 days from first launch, no account needed. When it ends, only starting a new search or indexing a new folder is gated — everything you’ve already indexed stays fully usable.

How big does the index get?

Roughly 1–2 GB per 100,000 photos, stored in one database file on your drive. Your original photos are untouched and not copied.