KittyLitter vs Models Zoo
Price, ratings, monetisation and update history for both apps, side by side — with what reviewers say about each.
KittyLitter
This app provides a native mobile interface for interacting with Codex servers. It allows users to manage coding sessions remotely, review conversation history, and communicate with the AI using voice input, all without needing a laptop.
- Discover local Codex servers
- Connect to remote servers via SSH
- Voice input for AI prompts
- Review conversation history and code
- Mobile-native UI
- Stay connected to your own servers
Read full descriptionHide full description
Litter is a native mobile client for Codex. Connect to local or remote Codex servers, manage coding sessions from anywhere, and keep conversations moving without opening your laptop. Features: - Add a direct server endpoint, connect over SSH, or pair with Alleycat by QR code - Connect to remote machines over SSH and start Codex remotely - Talk to Codex with voice input for fast, hands-free prompts - Review conversation history, reasoning, code blocks, and images in a mobile-native UI - Keep coding sessions on servers you control, with optional Alleycat relay pairing and OpenAI voice processing Litter is open source and built for people who want their coding agent with them wherever they are.
Models Zoo
Explore and experiment with various AI models directly on your device. This app allows you to chat with language models, generate images, process audio and video, and inspect model performance without needing a server or account. It's designed for developers to easily integrate AI into their own applications.
- On-device AI model catalog
- Chat with language and vision models
- Image generation and manipulation
- Audio processing and speech synthesis
- Model inspection and benchmarking
- Swift code export for integration
- Privacy-focused local inference
Read full descriptionHide full description
Core ML Models is a curated, on-device AI playground. Download any model from the built-in catalog and try it out instantly — no server, no account, nothing leaves your device. Every model is an open-source release converted from PyTorch to Apple's Core ML format and tuned to run efficiently on the Neural Engine, GPU, or CPU. WHAT YOU CAN DO • Chat with small language models (Gemma, etc.) including multimodal vision+text • Generate images from text with Hyper-SD • Remove backgrounds, matte video subjects, and colorize old photos • Estimate depth and reconstruct 3D faces from a single photo • Detect and classify with YOLO, SigLIP, and zero-shot open-vocabulary models • Separate music stems with Demucs and transcribe audio to MIDI with Basic Pitch • Clone voices and synthesize speech with Kokoro and OpenVoice • Super-resolve images with SinSR and RealESRGAN. DEVELOPER TOOLS, NOT JUST A DEMO • Inspect — see every .mlpackage's input/output tensor shapes, data types, compute-unit setting, on-disk size, and Core ML metadata at a glance. • Benchmark — run warmup + timed iterations on your own device and get average / median / min / max latency plus memory delta. Switch compute units (All, CPU+GPU, CPU+ANE, CPU only) to find the fastest config for your hardware. • Swift Code — export a ready-to-paste Core ML loading + inference snippet wired to the model's actual input/output names, so integration into your own app is copy-paste fast. DESIGNED FOR THE NEURAL ENGINE Each model ships with compute-unit settings tuned per-architecture (Neural Engine, GPU, CPU) so you get the best inference speed Apple Silicon can deliver. OPEN AND TRANSPARENT Every model in the catalog links back to its original paper, repository, and license. Conversion scripts are public on GitHub so you can see exactly how the .mlpackage files were produced. PRIVACY FIRST All inference runs locally on your device. The app only fetches model files from public storage over HTTPS — there are no analytics, no ads, and no account to create. REQUIREMENTS • iPhone or iPad with Apple Silicon recommended for best performance • Some large models require several GB of free storage and ≥ 6 GB RAM
Screenshots
Verdict
The clearest difference is rating: KittyLitter at 4.8 against Models Zoo's 3.0. KittyLitter also leads on ratings volume (45 vs 2). Models Zoo's advantage is in-app purchases (none vs 4). On price, update cadence, ads and monetization model there is nothing between them.
Scored on Price · Rating · Positive reviews · Number of ratings · Update frequency · Ads · In-app purchases · Monetization · Best chart rank · Devices · Requires iOS
Both are free to download. KittyLitter sells 4 one-off in-app purchases. Models Zoo asks for nothing beyond the download.
KittyLitter holds the better App Store score, 4.8 against 3.0. That said, the two scores are not equally well evidenced: KittyLitter has 45 ratings behind it against 2, so its average is the more settled of the two.
Both ship on a similar rhythm, roughly weekly. Both last shipped on November 15, 2026.
| Parameter | KittyLitter | Models Zoo |
|---|---|---|
| Price | Free | Free |
| Rating | 4.8 (45 ratings) — better | 3.0 (2 ratings) |
| Positive reviews | 100.0% of reviews | — |
| Number of ratings | 45 — better | 2 |
| Update frequency | Weekly | Weekly |
| Ads | No | No |
| In-app purchases | Yes | No — better |
| Monetization | Free | Free |
| Devices | iPhone, iPad, Apple Watch — better | iPhone, iPad |
| Requires iOS | 18.0 | 18.0 |
| Further details — not scored | ||
| Size | 150 MB | 13 MB |
| Age rating | 4+ | 4+ |
| Developer | sherif cherfa | Daisuke Majima |
Customer experience
KittyLitter
Models Zoo
In-app purchases
KittyLitter
- $9.99 Tip$9.99
- $24.99 Tip$24.99
- $49.99 Tip$49.99
Show 1 moreShow fewer
- $99.99 Tip$99.99
Models Zoo
No in-app purchases









