Tangerine Index lists products launched since ChatGPT and people's reactions to them.
DigUp
github.com
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
DesktopOpen source
Reactions (1)
Similar products
by description similarity
Docu Dig
AI-DrivenSmart Search for Your Documents
- Hacker News
- No reaction
- Product Hunt
- 126 votes
- GitHub
- No reaction
ManePaw
Find documents on your Mac using natural language
- Hacker News
- No reaction
- Product Hunt
- 85 votes
- GitHub
- 40 stars
Unfold
Extend macOS Quick Look to folders, archives & code files
- Hacker News
- No reaction
- Product Hunt
- 113 votes
- GitHub
- No reaction
Find images by what they show, AI-rename them, and sort them easily
ImageSage finds the image you remember. It is a private, local AI gallery. Point it at the folders you choose and it reads them in place, building an index that stays on your PC. That gives you two things Windows file search cannot: search that understands what is inside your images, and AI that renames them for you. INTELLIGENT SEARCH Type what you remember. Ordinary words become one natural-language query that runs against visual meaning and recognized text at the same time. - Visual meaning: "tiger looking out from a window" finds the photo even when nothing in the filename or the text says so. - Recognized text: on-device OCR reads the words inside screenshots, receipts, slides, error messages, and diagrams. Quote a phrase when it must match exactly. - Precise refinements: add filename:, path:, folder:, date:, type:, scope:, and sort: when you need them. Everything else stays plain language. Results stream in as you type and keep improving while a newly added folder finishes preparing, so you are never blocked waiting on an index. Save a search you will run again as a Smart Collection. Smart Collections are saved rules, not copied folders, so they always reflect your current library the next time you open them. Then act on what you found. Selection works directly on search results, so a set no folder view could produce - every screenshot mentioning "invoice", spread across six folders - can be moved, copied, renamed, or recycled in one pass. Other photo apps send you to File Explorer and lose your selection. ImageSage finishes the job on the real files, in the real folders. MAGIC RENAME "Screenshot (137).png" tells you nothing a year later. Select one photo or a hundred, choose Magic rename, and ImageSage proposes a short, descriptive filename for each one, using a generative AI model packaged inside the app and run on your device. Every suggestion is identified as AI-generated and opens in an editable review list. Change any name, exclude any file, and nothing on disk changes until you confirm. AI suggestions can be inaccurate or inappropriate and can be reported from Settings. PRIVATE BY DESIGN No ImageSage account. No ads. No developer analytics. Your photos, recognized text, searches, and visual-search data are never uploaded to an ImageSage cloud service. OCR, visual search, and Magic Rename all run on your device, and the catalog, thumbnails, and indexes stay under your Windows account. Online-only OneDrive files are ignored rather than downloaded. You can delete every piece of ImageSage-controlled local data without touching a single original photo. BUILT LIKE A GALLERY - Image-first gallery with River and Square layouts and three thumbnail densities - Expandable This PC tree: a registered root shows every image beneath it - Thumbnails appear progressively while indexing continues in the background - Explicit commands act on the originals themselves, in the folders Explorer already shows; indexing never reorganizes anything on its own - Double-click opens the original in your default Windows image viewer Supported formats: PNG, JPEG, and WebP.
- Hacker News
- 10 pts
- Product Hunt
- No reaction
- GitHub
- No reaction
Quello
One place to ask, across everything you already use.
- Hacker News
- No reaction
- Product Hunt
- 92 votes
- GitHub
- No reaction
