Security●●Solid
HideMyData – macOS PII Removal with Local AI and OCR
Local MLX model redacts PII without sending documents to the cloud.
Solve My ProblemCozy
maciejonos
201mo ago
Back to browse
GitHub Repository
1 starsSwift
Rampart on CoreML
by narner·Jun 30, 2026·6 points·2 comments
AI Analysis
●●●BangerSolve My ProblemNiche GemDark Horse
Runs Rampart PII model locally on iOS without calling AWS Comprehend APIs.
Strengths
- •Swift package handles model download and caching automatically on first use.
- •Includes validation script to verify Core ML parity against upstream ONNX predictions.
- •CLI and iOS example demonstrate real-world integration beyond just library code.
Weaknesses
- •Limited to Apple ecosystem; no Android or Linux server deployment options.
- •Relies on upstream Rampart model updates rather than maintaining independent improvements.
Category
Target Audience
iOS and macOS developers building privacy-focused applications
Similar To
Microsoft Presidio · AWS Comprehend · Google Cloud DLP
Post Description
CoreML implementation of National Design Studio's Rampart PII detection model + Swift package
Similar Projects
AI/ML●●Solid
On-device embedding and vector search for Apple Devices, built in Zig
Manually converting PyTorch models to CoreML so you don't have to call cloud APIs.
Niche GemWizardry
mcdow
203mo ago
AI/ML●●●Banger
On-device meeting transcription for your Mac
CoreML models on Apple Neural Engine beat Whisper.cpp for on-device transcription.
WizardryDark Horse
paynedigital
603mo ago
Developer Tools●●Solid
LocalCode – turn plain English into CLI commands with Apple's local AI
Native Apple Foundation Models integration is neat, but Warp already owns this space.
Ship ItNiche Gem
rahlokzero
3021d ago
Productivity●●Solid
Ratschn – A local Mac dictation app built with Rust, Tauri and CoreML
CoreML Whisper on Apple Neural Engine beats cloud APIs like Superwhisper.
SlickSolve My Problem
Edos8877
423mo ago
AI/ML●●Solid
I ported OmniAID image detection model to Apple's Neural Engine
Runs OmniAID detection locally on Neural Engine instead of uploading your data to servers.
SlickBig Brain
woadwarrior01
402mo ago