Grit for GitLab vs CoreAI Zoo

Grit for Gitlab is a native client for accessing GitLab on the go. Browse GitLab source repositories anytime, anywhere as long as you've got an internet connection. Grit visualizes your source code repositories, MRs, build pipelines, and review discussions in a beautiful UI that adapts with accessibility features in the app settings and the modern Liquid Glass interface(s). Grit is entirely open-sourced, available freely for auditing, forking, or contributing to help make the GitLab community better together! Grit was built with love to help bring the power of GitLab making GitLab more accessible to everyone. That being said, Grit for GitLab contains a number of useful features and functions to help you be productive on the go. From within this app, you have the functionality to: - Browse Public GitLab repositories - Browse your personal GitLab repositories - Merge open merge requests - Comment on Issues and open merge requests - Create new Issues - Mark issues as complete - View build pipelines (latest and historic) for repos that you have access to - View user profiles and contributor profiles for repositories - Follow other users, and view ongoing activity within Gitlab and projects you care about Grit for Gitlab is entirely and 100% free to use was you'd like. There is a tip jar, but please do not feel pressured, unless you want to contribute to development in that way. In any case, thank you for your support and I sincerely hope this app will be helpful to you and your everyday projects. Finally, Grit has been built with Apple's latest Foundation models included. This feature is entirely optional, disabled by default. When enabled, however, will provide you with an easily summonable assistant to help with summarising repositories, ask questions about source code, and summarise MRs that maybe are a bit challenging to understand. Note that this feature in particular is still a little experimental, and continual improvement to the hooks for the foundation models to work are still being worked on!

CoreAI Zoo puts the open-weight AI model zoo on your iPhone, iPad and Mac. Pick a model, download it once, and run it entirely on your device. No account, no server, and nothing you type, say or photograph ever leaves the device. CHAT Stream answers from open language models such as Qwen3, Gemma, LFM2.5, Granite and Mistral, from 0.6B to 30B+ parameters depending on your device's memory. Vision-language models (Qwen3-VL, MiniCPM-V, LFM2.5-VL) answer questions about your photos. VISION Ask questions about an image, read text with on-device OCR, and describe what the camera sees. AUDIO Transcribe speech with Whisper large-v3-turbo, Parakeet and Qwen3-ASR. Talk to an audio-understanding model, generate speech with Kokoro and VoxCPM, and try on-device music generation. CAMERA Live depth estimation, object detection (YOLOX, RF-DETR), action recognition and super-resolution on the camera feed. TOOLS Experimental models such as diffusion-based language models. BENCH Measure load time, tokens per second and memory for any chat model on your own hardware. HOW IT WORKS Every model runs through Core ML on Apple silicon. Weights are downloaded from the Hugging Face Hub on first use over HTTPS, then cached, so the app works offline afterwards. One model is resident at a time to stay within memory limits. New models arrive through a live catalog without an app update. GETTING STARTED Start with Qwen3-0.6B (454 MB) for the fastest first run. Larger models state the free space and memory they need; a recent iPhone Pro or an Apple silicon Mac runs the mid-size ones comfortably. Model weights follow their own licenses, listed on each model's Hugging Face page. The app itself is BSD-3-Clause and part of the open CoreAI model zoo. Report issues and request models at github.com/john-rocky/coreai-model-zoo.