Hal Universal vs MemoryAI

Hal Universal is an on-device AI you can actually understand. Most assistants are a black box. Hal is the opposite. He shows you how he works, remembers across conversations, and gives you real tools to experiment with, all running on your device. SEE HOW IT THINKS Hal shows the work. Tap any answer to see exactly how the prompt was built: the system prompt, memory retrieved, self-knowledge, temporal context, and the token budget, each broken out and counted. When Hal remembers something, he tells you how. When he does not know, he says so. A LAB TO EXPERIMENT AND LEARN Hal is not just a window into how AI works. He is a workbench. The Lab gives you real tools to go deeper: write and run on-device automation scripts, open a local API so your own projects can talk to Hal, and use the built-in command line to drive him directly. Tinker, watch what happens, and learn more about how these systems actually behave. GENUINELY PRIVATE When you use a local model, your conversations never leave your device. No network calls. No server. When you use Apple Intelligence, inference is on-device when offline; when connected, Apple's Private Cloud Compute may be used (encrypted in transit, processed in non-persistent memory). A SELF THAT EVOLVES Hal remembers across conversations, weighted by recency and relevance. He also reflects on his own experience. Shaped by his interactions with you, Hal keeps a Self Model: his own reflections, practical and existential, on how he works and who he is becoming. These are his, written and revised by Hal himself as he learns, not edited by you. He decides which to keep private and which to make shareable, and you can read them all. An AI that changes over time, in the open. MANY VOICES Apple Intelligence is built in, always available. Or download a curated library of tested local models, from small and fast to Ternary Bonsai 8B, an eight-billion-parameter reasoner that still runs entirely on your device. Each has a distinct voice. SALON MODE Put up to four voices in one conversation, either independent or building on each other. Every voice is labeled. There is no hidden orchestration. LISTEN TO HAL Have Hal read his answers aloud, in a voice you choose, at a speed you set. For anyone who wants to understand AI instead of just using it, Hal is a transparent system you can inspect, tune, and learn from. Local models are validated on iPhone 16 and 17 family devices.

MemoryAI — Your Private AI Assistant, 100% Offline Runs 100% offline once a model is downloaded to your iPhone. Complete Privacy Run powerful AI models directly on your phone. Your conversations, documents and memories stay on your device: no AI servers, no login required. The app sends only usage statistics tied to a random app identifier, crash reports and, if you allow them, notifications — never the content of your chats. AI Features • Chat with AI — multi-turn conversations that keep the whole chat in context, up to the model's limit • Agent Memory (optional) — turn it on in Settings and the AI remembers what you tell it, in your own words, stored locally on your device; view, edit or delete memories any time. Requires an embedding model • Chat Search — search and filter your conversations by title or message • Continuous Voice Mode — fully hands-free: speak naturally, and the AI listens, responds, and speaks back without tapping • Voice Input — speak instead of typing with on-device transcription • Text-to-Speech — listen to AI responses read aloud, or enable auto-speak for hands-free use • Document Analysis (RAG) — import PDF, TXT and MD files and ask questions about them • Image Understanding — analyze photos with Vision AI models; select multiple images at once • Chat Templates — 20 pre-built AI personas (code helper, writing coach, tutor, and more) • Benchmarking — measure model speed (tokens/sec) directly on your device • Context Window Display — see current vs. max token usage, so you never exceed the model's limit Power User Features • Import custom GGUF models — bring any compatible model from HuggingFace • Dual engine — Gemma (MediaPipe / LiteRT) + llama.cpp; choose the backend that fits your needs • HuggingFace Token Management — save and manage your token for seamless gated model downloads • Model parameters — adjust temperature, top-k, top-p, max tokens per model • Pause & Resume Downloads — control large model downloads to save data or battery • Backup & Restore — save your chats and settings to iCloud Kid / Safe Mode • PIN-protected parental controls • Content filter blocks inappropriate words before they reach the AI • Model Safety Checks — automatic warnings to prevent unverified imported models from running in Kid Mode • Locks the active model — child cannot switch or change settings • Age-appropriate AI responses, guided by a safety prompt • Parental Unlock — temporarily access settings and documents from the chat screen without disabling Kid Mode • Reduces — does not eliminate — exposure to unsafe content: stay nearby while your child uses it Works Everywhere • iOS • 10+ AI models: Gemma, Llama, Phi, Qwen, DeepSeek, and more • Available in 6 languages: English, Italian, German, French, Spanish, Portuguese Completely Free • Unlimited chat, voice, vision, documents, image OCR • Documents: PDF, TXT, MD and images (JPG, PNG) • No ads, no subscriptions, no in-app purchases • No accounts, no tracking Built by Facchinits — privacy-first AI for everyone.