conscious-engines

conscious-engines / modelhub

Public

One hub for all LLMs. Lives on your macOS menu bar.

studio.consciousengines.commodel-hub
18
1
100% credibility
Found Apr 29, 2026 at 18 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Swift
AI Summary

A macOS menu bar application that scans local AI model directories, enables browsing and downloading from Hugging Face, and provides tools for sorting, searching, and deleting models.

How It Works

1
🔍 Discover Model Hub

You hear about a handy menu bar app that organizes your scattered AI models from different tools into one easy list.

2
📥 Download and install

Grab the app from the releases page, drop it into your Applications folder, and it appears quietly in your menu bar.

3
🧠 Click the cube icon

Tap the cube in your menu bar to open a beautiful list of all your local models, sorted neatly with sizes and dates.

4
🔄 Switch tabs to explore

Flip to the Explore tab to search Hugging Face models live, see previews with sizes, and download with one click right from the menu.

5
📱 Search and sort your list

Type to filter your models instantly, sort by size or date added, and spot which ones are currently loaded with a pulsing green dot.

6
🗑️ Manage easily

Copy a model's ID to paste anywhere, reveal folders in Finder, or trash ones you don't need after a quick confirmation.

✅ Everything organized

Now all your models live in one spot, downloads flow seamlessly to where your tools expect them, and managing feels effortless.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 18 to 18 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 modelhub?

Modelhub is a Swift-based macOS menu bar app that centralizes management of local LLMs, scanning LM Studio and HuggingFace cache directories to list every model in one spot. It solves the chaos of scattered models across tools by offering search, sorting by size or date, a pulsing dot for LM Studio-loaded models, and one-click downloads from HuggingFace that land in the standard cache—ready for transformers, mlx-lm, or ollama. No Dock icon, just click the cube for instant access.

Why is it gaining traction?

Unlike CLI tools or browser tabs, it lives in your menu bar for zero-context-switching workflow, with live search filtering locals or fetching HF text-gen models, plus copy-ID, Finder reveal, and trash actions. One-click github one key downloads pause/resume with progress, and totals update on filter—features that hook devs tired of terminal hopping. As a one hub app, it unifies what LM Studio and HF CLI scatter.

Who should use this?

macOS devs running local inference via LM Studio or HuggingFace cache, especially those prototyping with Qwen, Llama, or Gemma variants and needing quick scans without firing up apps. Ideal for ML tinkerers juggling downloads, who want a glanceable overview with loaded status and bulk management before loading into one pace workflows.

Verdict

Grab the release for a lightweight LLM hub if you're on macOS—it's polished for daily use despite 18 stars and 1.0% credibility signaling early maturity. MIT-licensed with solid docs, but watch for gated-model auth in future updates.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.