MacPaw

MacPaw / Gliner2Swift

Public

Swift port of Gliner2 framework

ai-lab mnemos trd
19
0
100% credibility
Found Feb 20, 2026 at 15 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Swift
AI Summary

A Swift package porting the GLiNER2 AI model for extracting entities, classifying text, and structured data from natural language on Apple Silicon.

How It Works

1
🔍 Discover GLiNER2Swift

You find this helpful tool that makes it easy to pull names, companies, and key info from everyday text.

2
📦 Add to your app

Simply tell your Swift project to include this friendly assistant with a quick setup.

3
🧠 Bring the model to life

It automatically grabs a smart thinking model and gets ready to understand your text.

4
📝 Feed it some text

Share a sentence and tell it what to look for, like people or places.

5
✨ See the magic happen

Watch it highlight exactly the names, companies, or feelings right where they appear.

🎉 Your text is now smart

Your app effortlessly extracts useful info, making everything smarter and easier.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 15 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Gliner2Swift?

Gliner2Swift ports the Gliner2 framework to Swift, letting you extract entities, classify text, and pull structured data from natural language using simple schemas. Drop it into macOS or iOS apps via Swift Package Manager for on-device inference on Apple Silicon—no GPU, no Python dependencies. It handles NER like spotting people/companies/locations, plus relations and JSON-like outputs, all with ~50ms latency per sentence.

Why is it gaining traction?

This Swift GitHub repo stands out by bringing Python-level NER to native Swift apps, with full numerical parity to the original and automatic Hugging Face model downloads. Developers love the schema builder for custom extraction—like defining "person" or "sentiment"—without regex hacks or heavy ML libs. CPU-first design via Apple's MLX crushes it on M-series chips, perfect for swift GitHub projects needing real-time text processing.

Who should use this?

macOS/iOS devs building search tools, note apps, or analytics dashboards that parse user text for entities/relations. Ideal for indie hackers prototyping swift GitHub actions or apps like content analyzers, where you need schema-driven extraction without cloud APIs. Skip if you're not on Apple Silicon or need training/fine-tuning yet.

Verdict

Grab it for prototyping schema-based extraction in Swift apps—solid API, quick start, and parity tests show promise despite 15 stars and 1.0% credibility score. Still WIP (no training/relations), so pair with the Python original for production until more models land.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.