AILY – Local & Cloud AI

AILY runs large language models directly on your iPhone — no internet required. TRUE OFFLINE AI Download any of 20 popular open-source LLMs — Qwen, Gemma, Llama, Phi, SmolLM, DeepSeek distills and more — and chat entirely on-device, powered by llama.cpp. Airplane mode, the subway, a flight, a trip abroad with no data plan: your AI keeps working. Nothing you type ever leaves your phone, and there is no per-message cost — ever. • 20-model library, from 0.5 GB pocket models to 4 GB+ flagships • One-tap download with smart region routing and auto-retry • Memory guard: AILY warns you before loading a model your iPhone can't handle, and suggests a lighter one • Import any custom GGUF model from Files APPLE ON-DEVICE MODEL A second fully offline engine, powered by Apple Intelligence — free to run, instant, and private (requires iOS 26 or later). CLOUD APIs — OPTIONAL, YOUR KEYS When you want frontier-level power, bring your own API key to connect Claude, GPT, DeepSeek, Kimi, GLM, Qwen, Gemini, Grok, or a local Ollama server. Endpoints come pre-configured; just paste your key. Keys are stored in the iOS Keychain and connect directly to official endpoints — no middleman, no markup. ONE PURCHASE, EVERYTHING INCLUDED AILY is a one-time purchase: no subscription, no in-app purchases, no ads. Buy once and every feature is yours forever, including future updates. MORE REASONS TO LOVE AILY • Zero data collection — no account, no server, no analytics • Vision input — attach photos and let vision-capable models read them • Streaming replies with one-tap stop, conversation history, photo chat GOOD TO KNOW • Local models work fully offline after a one-time download • Cloud providers require your own API key and bill you directly at official rates • AI-generated content may contain errors — please verify important information