CoreAI Zoo vs RuntimeBrief

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.

RuntimeBrief turns activity from your local coding agents and repositories into short, evidence-backed project updates. Connect the app to the RuntimeBrief daemon running on your Mac to see what changed, what is still in progress, and what needs your attention. Each claim links back to its supporting commit, working-tree scan, or agent session. Features: • A concise portfolio brief across your registered projects • Evidence-backed project status and recent agent activity • Native Claude Code, Codex and Cursor tasks in registered projects with model and permission choices and provider-supported native handoff • Optional, on-demand analyst answers through your own Codex CLI login • Local Xcode, TestFlight, and App Store release summaries • Siri and Shortcuts access to project status • Saved briefs when your Mac is temporarily unavailable • A fully offline fictional demo requiring no account or server RuntimeBrief has no hosted account, analytics SDK, advertising SDK, or public cloud relay. Live project data stays under your control on your Mac and private network. Optional analyst processing follows the data controls of the ChatGPT workspace selected in Codex CLI. Native tasks use your existing provider login and follow that provider's account policies and the selected tool permissions. A Mac running runtimebriefd is required for live project data. The in-app demo can be explored without installing or configuring anything. Native tasks require the selected coding agent installed and signed in on that Mac. Provider-supported handoff also requires the corresponding native desktop app.