Local AI · Mac · Windows

Your photo library. Type it. Find it.

Type “sunset” — get sunset photos. Type “mom holding the cake” — get that. RetinaTag indexes every photo on your Mac or PC with on-device CLIP and local Ollama models. Nothing leaves your machine. Ever.

100% free · forever No subscription, no card Offline by default
Local CLIP semantic search Local Ollama tagging Apple Silicon · CUDA Private vault · Touch ID XMP sidecars 100% free Offline by default
The problem

Years of photos. Zero of them findable.

Apple Photos searches for what's tagged. Lightroom searches for what you tagged. iCloud charges you forever to lose them in the cloud. Meanwhile that one photo of your dog at the beach — it's in there, somewhere.

Without RetinaTag

Twelve folders deep, sixty thousand thumbnails to scroll through.

You know the photo exists. You took it. It's somewhere in there. Apple Photos won't find it because it doesn't know what you mean. Lightroom won't find it because nobody tagged it. The cloud will charge you ₺99/ay forever to keep it lost.

With RetinaTag

Type the feeling. Get the photo.

RetinaTag reads every photo on your machine with local AI. CLIP understands “sunset over the sea.” Ollama writes natural-language captions. The result: a search box that knows what you mean, even when you don't quite know what you took.

How it works · 4 steps

Install. Point. Wait. Search.

No setup wizard hell. No “invite your team.” You install RetinaTag, point it at the folders that hold your photos, and walk away. By the time you come back, every picture is searchable by what's in it.

  1. 01

    Install & pick a library.

    Drop the macOS or Windows installer. On first launch RetinaTag asks where your photos live — your Pictures folder, an external drive, a NAS share, anywhere. Add as many roots as you want; remove them later without losing tags.

  2. 02

    Models download themselves.

    RetinaTag detects your machine and recommends a CLIP tier and an Ollama model that will fit your hardware. One click downloads them in the background. Files come straight from Hugging Face and Ollama — never our servers.

  3. 03

    Indexing in the background.

    Photos get a CLIP embedding (~10 ms each on Apple Silicon) and an Ollama caption (~1–2 s each). You can search the moment indexing starts; new results stream in as more photos finish processing. Pause / resume anytime.

  4. 04

    Search by feeling.

    Type "mom holding the cake." Type a year. Type a place name. Type a color. Type Turkish. RetinaTag understands what you mean — even on photos you never tagged a day in your life.

01 Main view · all your photos at a glance

Hundreds of thousands of organized photos.

This is RetinaTag — the Gallery view. The top toolbar flips between Gallery, Timeline, Map, Cleanup, Dashboard, Calendar, Vault — seven views over the same library. The sidebar mirrors how you actually think: every folder you've added (with photo count), every Collection you've stacked, every face cluster, every AI provider you've configured. The status row shows what's tagged, what's pending, and what your tagging has cost (almost nothing — Ollama is free). Click any thumbnail to dive into a detail panel with the full AI tag set.

  • Seven views, one app — Gallery, Timeline, Map, Cleanup, Dashboard, Calendar, Vault.
  • Sidebar = your library's map — folders, favorites, collections, people.
  • Live counts — photos / tagged / pending / total cost.
  • Bulk operations — Tag with AI, Identify Faces, Export — on multi-select.
RetinaTag's main Gallery view — hundreds of thousands of photos in a grid with sidebar showing folders, AI providers, and stats
Gallery · your full library · live counts · <$0.01 total cost
02 AI tags · 16+ attributes per photo

Every photo gets a written description.

Open any photo and you see what the local Ollama model saw: a list of sixteen-plus named attributesperson · happiness · indoors · gray sweater · childhood · portrait · intimate · love · parent · photography — each scored at 100% confidence. Plus a one-sentence written caption (“A woman and a child are smiling closely together indoors, capturing a moment of warmth and affection”). Star-rate, copy a tag, mark a favourite, refresh tags from a different model. All searchable from the same search box, all exportable as XMP — your tags travel with the file even if you stop using RetinaTag.

  • Sixteen-plus attributes — color, mood, scene, subject, action, all named.
  • Written caption — one sentence, in English or Turkish or whatever you ask.
  • Star ratings + favourites — your manual layer over the AI's.
  • Refresh from a different model — see what Qwen vs Gemma sees differently.
RetinaTag photo detail panel showing 16 AI-generated tags at 100% confidence: Yasemin, care, child, childhood, close-up, dark background, emotions, family, gray sweater, happiness, indoors, intimate, love, parent, photography, portrait
Photo detail · 16 tags · written caption
04 Local Ollama · vision LLMs

Pick your model. Pick your VRAM.

Ollama runs vision-language models entirely on your machine. RetinaTag inspects your GPU and recommends a model that will actually fit your VRAM — Moondream 2 (1.5 GB) on a thin laptop, Qwen2.5-VL 7B (5.5 GB) on a 16-GB rig, Qwen2.5-VL 32B (20 GB) if you have an RTX 4090. Every photo gets a real, written description in plain English (or Turkish, or whatever you ask the model to generate). Captions are searchable from the same search box and exportable as XMP sidecars.

  • Six curated models — Moondream 2, Gemma 3 4B/12B/27B, Qwen2.5-VL 7B/32B.
  • VRAM-aware — RetinaTag tells you which models will run before you download.
  • Plain-English captions — searchable, exportable, your-language-able.
  • Bring your own server — point to a remote Ollama instance over HTTP.
RetinaTag's Ollama model picker showing six vision-language models with VRAM requirements: Moondream 2 (1.5 GB), Gemma 3 4B (3.5 GB), Qwen2.5-VL 7B (5.5 GB), Gemma 4 12B (9 GB), Qwen2.5-VL 32B (20 GB), Gemma 4 27B (18 GB)
Local Ollama · 6 models · 1.5–20 GB VRAM
05 Library navigator · folders · collections · people

One sidebar. Everything you organize.

The sidebar is your library's map. Add a folder, it appears with a live photo count. Make a Collection — “Wedding,” “Stuff to print,” “2014 Paris” — and drag photos into it. The People panel toggles between automatic Cluster mode (faces grouped by similarity) and Recognize mode (you've named some, the others get matched to them). At the bottom, the AI Provider switch shows Local (Ollama) by default — free and private — with an image-counter and a running cost-tracker that always reads <$0.01 unless you've turned on a paid cloud model.

  • Folders + Favorites — automatic, file-system mirrors with live counts.
  • Collections — your hand-curated stacks, drag-and-drop.
  • People — Cluster (auto) or Recognize (after you've named some).
  • AI Providers — local Ollama by default, BYO API for cloud models.
RetinaTag's left sidebar showing Add Folder button, folders list, Collections, People with Cluster/Recognize, AI Providers toggle, and live stats for photos / tagged / pending / total cost
Sidebar · folders · collections · people · costs
06 Timeline navigator

Years and months. One scrubber.

A two-row scrubber along the top of the gallery. The top row is years; the bottom row is months. Drop into October 2025 in one click; see 478 photos from that month, surrounded by every other month around it. Counts under each year tell you where the dense periods are — that 2024 wave you forgot, that quiet 2021 valley. The timeline reads EXIF date-taken (not file modified), so the chronology is the real one — even for photos that bounced through a backup, a re-import, a system migration. Arrow keys jog you through one month at a time.

  • Two-row scrubber — years on top, months on the bottom.
  • Photo counts per year and per month, always visible.
  • Keyboard nav — arrow keys, page up/down, home/end all work.
  • Reads EXIF date-taken — survives re-imports and file copies.
RetinaTag's year-by-year timeline scrubber — years visible with live photo counts beneath each, current month highlighted
Year-month scrubber · EXIF date-taken · live counts
07 Map view · Globe · Flat · Heat Places

Every photo with GPS, on a map.

A pin for every photograph that has GPS in its EXIF. Three lenses on the same data: Globe (3D earth, drag to rotate), Flat Map (Mercator, infinite pan), and Heat Places (density gradient — see at a glance where you've spent the most time). Click a pin and the right panel opens: the photo, its location reverse-geocoded to a place name (“At Marrakesh, Morocco”), date, EXIF, and the tags Ollama wrote for it. Filter by tag first, then look geographically — find every photograph you took that contains “architecture” overlaid on the map.

  • Globe / Flat / Heat — three lenses on the same EXIF data.
  • Click a pin → photo + reverse-geocoded place + tags + EXIF.
  • Filter by tag, see where you took “architecture” shots geographically.
  • Reverse geocoding — “Marrakesh, Morocco” not “31.6, -8.0”.
RetinaTag's Map view showing photo pins across Europe, Africa, and Middle East — one selected pin shows a photo titled DSC08164.JPG taken in Marrakesh, Morocco with tags including architecture, building, contemplation, desert, dust
All your geo-tagged photos · Globe / Flat / Heat · reverse-geocoded
08 Private vault · PIN unlock

Photos that don't show up. Even on the same machine.

A vault that's invisible until you unlock it. Files encrypted with a PIN-derived key (Argon2id + AES-GCM). The unlock dialog reveals nothing about what's inside — no thumbnail count, no preview, no leak. Photos in the vault don't appear in any timeline, search, or library cleanup until you type the PIN. The recovery code is optional: keep one and you can recover from a forgotten PIN; skip it and the vault is gone forever after ten wrong tries — that's the point.

  • Argon2id + AES-GCM — modern, audited cryptography.
  • Vault-locked = invisible — no leaks to search, timeline, or cleanup.
  • Recovery code optional — keep one or live dangerously, your call.
  • 10 strikes — wrong PIN ten times, vault wipes itself, silently.
RetinaTag's Private Vault unlock dialog — PIN entry field with hidden text, Forgot PIN recovery option, copper Unlock button
Vault unlock · PIN protected · 10 attempts max
09 Auto-lock · Touch ID · paranoid mode

Idle for 5 minutes? The vault locks itself.

RetinaTag tracks mousemove and keydown globally and checks every 30 seconds. The instant your idle window crosses your auto-lock threshold, the vault locks and any open modal showing vault content is dismissed. Want biometric unlock? Enable Touch ID and the master key sits in the macOS Keychain protected by your fingerprint. Adding or removing fingerprints in System Settings invalidates the Keychain item — by design, so a stolen laptop with new fingerprints can't open the vault.

  • Auto-lock — 30 s to 60 min idle, or never.
  • Touch ID on macOS — Keychain-stored, biometry-protected master key.
  • Fingerprint changes invalidate — re-enable Touch ID after Settings tweaks.
  • Globally tracked — works even when RetinaTag isn't focused.
RetinaTag's Vault settings panel — auto-lock slider set to 5 min idle, recovery code warning, Touch ID checkbox
Auto-lock · Touch ID · Keychain-bound key
10 Device import · USB · SD · iPhone

Plug in. Photos sorted by date-taken.

Insert an SD card or USB drive — RetinaTag detects it and asks if you want to import. Files copy into a clean YYYY / YYYY-MM Month folder structure based on the EXIF date-taken, not the file's modified date. iPhone? On macOS, use the built-in Image Capture or Photos app first to pull originals off, then add that folder as a Watch Folder here. Drag-and-drop straight from Finder works too — RetinaTag indexes new files the moment they appear.

  • Auto-prompt — “Ask when a device is detected” toggle.
  • Date-taken folder structure — predictable, future-proof, OS-agnostic.
  • Watch folders — index automatically as files appear, even unattended.
  • iPhone-friendly — pair with Image Capture; no proprietary sync needed.
RetinaTag's Device Import settings — green toggle for 'Ask when a device is detected', destination folder picker with Browse button, instructions for iPhone via Image Capture
USB / SD / iPhone · auto-sort by date-taken
11 Library cleanup

Find duplicates. Get gigabytes back.

RetinaTag scans your library and counts what's duplicate, what's blurry, what's not yet analyzed, and exactly how much disk you'd reclaim by deleting the redundant copies. Duplicate detection uses a perceptual hash — same photo at different resolutions, different formats, different rotations all collapse to one. Tag a photo as a “keeper” (gold) or invest in it (blue — tag, rate, add to a collection) and RetinaTag will never auto-delete it, even if a heuristic says it should.

  • Perceptual hash — finds visual duplicates across formats and resolutions.
  • Blur scoring — surfaces the out-of-focus shots you scrolled past.
  • Keeper protection — gold (keeper) and blue (invested) photos are off-limits.
  • Reclaimable GB — exact byte-savings before you click delete.
RetinaTag's Library Cleanup dashboard showing duplicates count, gigabytes reclaimable, blurry photos count, and not-yet-analyzed count
Cleanup · duplicates · blurry · reclaimable GB
12 Maintenance toolkit

The boring stuff. Automated.

Seven one-button utilities for the work you didn't know you'd need. Fix Sideways Photos re-renders only the thumbs whose EXIF orientation is non-trivial — fast, never the whole library. Import Tags from XMP reads .xmp sidecars another machine wrote and pulls in tags, ratings, favourites — perfect for syncing libraries between your laptop and desktop. Regenerate All Thumbnails is the nuclear option. Health Check finds orphaned entries and missing thumbnails. Extract GPS and Dominant Colors re-run those passes on demand. Each button does one thing well — and is reversible, except the last one (clearing all tags), which is on purpose.

  • Fix Sideways Photos — smart EXIF-aware re-render, only what's needed.
  • Import Tags from XMP — sync libraries between machines via sidecar files.
  • Health Check — orphaned entries, missing thumbnails, broken refs.
  • Extract GPS / Dominant Colors — re-runs to fix sparse maps or enable Search by Color.
RetinaTag's Maintenance panel with seven buttons: Fix Sideways Photos, Import Tags from XMP, Regenerate All Thumbnails, Health Check, Extract GPS from EXIF, Extract Dominant Colors, Clear All Tags
Seven one-button utilities · all reversible (except the last)
13 Silent auto-updates · GitHub releases

A new version drops. You barely notice.

Ten seconds after launch, RetinaTag checks the official GitHub release manifest. If a newer signed build is available, a dismissible card slides in from the bottom-right offering one-click install + relaunch. No forced restart. No “please update” modal blocking your work. The builds are GitHub-signed — same artifacts you can verify yourself from the releases page. If you'd rather pull updates manually, toggle off the auto-check and the card never appears again.

  • GitHub-signed releases — same artifacts you can audit yourself.
  • Dismissible card — never modal, never blocks your workflow.
  • One-click install + relaunch — zero CLI fiddling, zero browser detours.
  • Toggle off if you prefer — your machine, your rules.
RetinaTag's About panel showing version 1.5.69 with a Check for Updates button and an auto-check toggle
v1.5.69 · GitHub release manifest · auto-check on launch
Privacy manifesto

Hundreds of thousands of photos.
Only you can see them.

No cloud upload. No telemetry on photo content. No license server. No account. CLIP runs locally. Ollama runs locally. The vault encrypts to your PIN. Everything is local. We literally cannot see your library — and we like it that way.

Download · 100% free

Pick your platform.
Both ship the same engine.

RetinaTag for Mac macOS 12+ · Apple Silicon · Intel RetinaTag for Windows Windows 10+ · x64 · CUDA optional
The price

Completely free.

Yes, really. No subscription, no “upgrade” tier, no “free trial” trick that locks you out on day 31. Download it, install it, use it forever. The whole feature set, every photo, every model.

FREE
No card. No account. No subscription. No telemetry. No upgrade tier.
  • Unlimited photo library
  • CLIP semantic search · 3 model tiers
  • Local Ollama — 6 vision-LLM models
  • Year/month timeline navigator
  • Private vault · PIN · Touch ID
  • USB / SD / iPhone import + watch folders
  • XMP sidecar export · Lightroom-compatible
  • Mac + Windows · all future updates
Download for Mac — free
Mac + Windows · runs locally · all updates included, forever
FAQ

Frequently asked questions.

Do you store my photos?
No. Everything runs on your own machine. Your photos never leave your device. We don't have a server that sees them.
What models actually run? Are they bundled?
CLIP (ViT-B/32 quantized) is bundled — the “Fast” tier downloads with the app. Larger CLIP models (ViT-B/32 full, ViT-L/14) and any Ollama model download on demand to a folder you pick. Nothing phones home; the model files come from Hugging Face / Ollama directly.
Do I need a beefy machine?
For semantic search, no — the “Fast” CLIP tier runs on any Mac and any modern Windows machine. For Ollama vision-LLM tagging, more is more: Apple Silicon with 16+ GB unified memory or NVIDIA with 8+ GB VRAM gives the best experience.
What's the catch? How is this completely free?
No catch. RetinaTag runs entirely on your machine — there are no servers we have to pay for, no GPU bills, no cloud storage, no per-photo tagging cost. The CLIP and Ollama models are downloaded once from Hugging Face and Ollama directly. We don't collect telemetry on your library. There's nothing to monetize, so nothing to charge you for.
One license, multiple machines?
Single-user license — use it on your own Mac and PC simultaneously. We don't enforce activation count; we trust you.
What's the vault — is it secure?
Photos in the vault are encrypted with a key derived from your PIN (Argon2id + AES-GCM). The unlocked master key sits in macOS Keychain or Windows DPAPI when Touch ID / Hello is enabled. Ten wrong PIN attempts and the vault wipes — no “backup,” intentionally.
Where does my library actually live?
Your photos stay where they are — in the folders you pointed RetinaTag at. RetinaTag keeps a SQLite index file alongside its own data folder; nothing is moved or copied unless you explicitly use Device Import. Uninstall RetinaTag and your photos are right where you left them, with optional XMP sidecars next to each file if you've enabled tag export.
Does Touch ID work on Windows?
On Windows, biometric unlock uses Windows Hello (fingerprint reader or face camera) backed by DPAPI for the master key — same protection model as macOS Keychain. If your machine doesn't have Hello hardware, the vault falls back to PIN-only.
Will you start charging for it later?
No. The version you download today will keep working — and stay free — as long as your operating system supports it. If we ever build a separate paid product (a cloud sync service, an enterprise tier, whatever) it'll be a separate product, not a paywall on this one. The standalone app stays free, forever.

Stop scrolling for that one photo.
Type how it felt instead.

Completely free. No subscription. No card. Yours forever.