Nicheloom visitors: 13,662 all-time · 8,824 in the last 7 days

The opportunity tracker for new startups.

Today: 2,299 launchs · Niche of the day: document and PDF processing tools · See full report →

DigUp

Search your Mac by what's in your files: photos, PDFs, recordings, videos and code. On-device, built on Google DeepMind's EmbeddingGemma 2.

Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.

This is 1 of 242 launches in macOS desktop and system utilities — see how it stacks up on momentum and crowding →

82 other launches read as similar to this one →

Details

External ID
1410929004
Source
GITHUB
Company
—
Product
DigUp
Website domain
github.com
Launched
Oct. 8, 2026
Cohort
—
Upvotes
1724
Upvotes percentile
1.00
Tags
embeddinggemma, embeddings, llama-cpp, local-first, macos, menubar-app, multimodal, on-device, semantic-search, swift

Enrichment

Niche
macOS desktop and system utilities
Vertical
Horizontal
Function
Search & retrieval
Audience
Prosumer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
local semantic search for mac files using embeddings
Manually corrected
False

Could you build this?

Partial The macOS client UI and pipeline are vibe-codeable, but running local multi-modal embeddings across diverse file types performantly on Apple Silicon requires specialized ML engineering.

What it would actually take: The app needs a native macOS daemon (Swift) hooked into FSEvents to track file changes, extraction parsers for photos, audio, code, and PDFs, and a local vector database (like SQLite with sqlite-vec). The difficult part is compiling and quantizing Google's EmbeddingGemma model with Apple MLX or CoreML to run efficiently without draining battery or causing thermal throttling during background indexing.

Competitors

Other products that read as similar to this one — 82 launches clear the similarity bar, closest 8 shown.

Attention rank: #3 of 83 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 216 days after the earliest competitor.

Other launches for this product