# Hal Universal — Private AI That Shows Its Work > Private AI That Shows Its Work (iPhone/iPad app by Mark Friedlander.) - Source: https://appshunter.io/ios/app/hal-universal/id6754847753 (this page in markdown: same URL + `.md`) - Developer: [Mark Friedlander](https://appshunter.io/developer/1812095304) - Category: Productivity, Education - Price: Free - Age rating: 4+ - Requires: iOS 26.0 · 30 MB - Languages: American English - Released: 2025-11-05 - Data updated: 2026-08-11 - User reviews in markdown: https://appshunter.io/ios/app/hal-universal/id6754847753/reviews.md ## What is Hal Universal? 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. ## Version history (last 5 releases) ### 3.0 — 2026-08-10 Hal's biggest update yet, and still entirely on your device. THE LAB, EXPANDED More tools to experiment with and learn from: on-device automation scripts, a local API for your own projects, and a command line to drive Hal directly. Transparency you can get your hands on. SEARCH EVERYTHING Find any word inside a conversation, or search across all of your conversations at once by title and content. A BUILT-IN GUIDE A new in-app guide and help system explains what Hal can do and how he works, right when you need it. LISTEN TO HAL Hal can now read his answers aloud in a voice you choose, at your own pace. CLEANER AND CLEARER A refreshed interface: a tidier toolbar, a privacy lock you can see at a glance, in-app search, and smoother navigation throughout. ### 2.5 — 2026-07-12 Hal keeps getting more capable — and more honest about how he works. • Ternary Bonsai 8B — Hal's deepest on-device model yet. An 8-billion-parameter reasoner that runs entirely on your iPhone, about as fast as the smaller models. • A privacy lock you can see. A lock in the toolbar shows at a glance whether Hal is in a state where data could leave your device. Tap it to understand why. • Sharper memory. More accurate long-term recall, an optional new embedding model, and rebalanced search so the right memories surface — and recent ones are weighted correctly. • Download models once. Models are shared with our companion app, so you don't re-download. • A more honest Hal. His self-reflections are now written in his own first-person voice, and his Self Model screen reads like plain language instead of raw data. When Hal doesn't have something in memory, he tells you — instead of guessing. • Smoother and steadier: faster model switching and loading, and settings that stick. ### 2.0 — 2026-05-21 Version 2.0 — significant update. - Four curated local AI models now available: Gemma 4 E2B, Llama 3.2 3B, Qwen 3.5 2B, and Dolphin 3.0. Each runs entirely on your device. - Self Model: Hal now builds a structured self-model of you over time from patterns in conversation. Browse and edit it in Settings → Self Model. Each entry is private by default. - Salon Mode: put up to four AI voices in conversation. Independent and context-aware modes. - Per-model settings: temperature, memory depth, RAG configuration saved independently for each model. - Upgraded retrieval (optional): Nomic Embed Text v1.5 available as an opt-in via Model Library — significantly better recall on specific facts than the default. 522 MB. - Per-turn memory pre-flight: when a turn would exceed the active model's working memory, Hal explains why in chat rather than crashing. - Real token streaming: responses stream as they generate. - Background downloads: model downloads continue while the app is backgrounded or the phone is locked. - Unified model status dots: one dot, one meaning across all screens. - Significant performance and stability improvements. ### 1.5 — 2025-11-15 What’s New in Version 1.5 This release brings major improvements to transparency, control, and cross-platform consistency. • Clearer On-Device Privacy Updated AFM vs. Phi-3 behavior with precise explanations of when AFM may use Apple’s Private Cloud Compute and how to ensure 100% on-device operation. • Timestamp-Aware Memory Hal now interprets recency using message timestamps, improving what he remembers and how context is weighed. • Expanded Power User Controls Adjust recency weighting, semantic relevance, memory half-life, RAG retrieval size, and temperature — with changes reflected directly in the chat. • Detailed Token View See a full token breakdown for each message in the detailed view. • Cross-Platform Parity Unified layout and behavior across iOS, iPadOS, and macOS, including a resizable Mac window. • Improved Usability Better keyboard dismissal on iPhone/iPad and clearer document upload status. • Restore Defaults One tap to reset all tuning parameters to the original factory settings. ### 1.0 — 2025-11-05 No release notes. ## Apps similar to Hal Universal | App | Rating | Price | Category | | --- | --- | --- | --- | | [Blank Spaces Launcher](https://appshunter.io/ios/app/blank-spaces-launcher/id1570856853) | 4.6 (8,066) | Free | Productivity | | [Yahoo Mail: Your Email & Inbox](https://appshunter.io/ios/app/yahoo-mail-your-email-and-inbox/id577586159) | 4.7 (4,763,792) | Free | Productivity | | [Remind Me Faster](https://appshunter.io/ios/app/remind-me-faster/id985555908) | 4.8 (448) | Free | Productivity | ## More apps by Mark Friedlander - [Reflect: Creative Sparks](https://appshunter.io/ios/app/reflect-creative-sparks/id6745411935) - [Pure Phase](https://appshunter.io/ios/app/pure-phase/id6767311034) - [Purr Machine](https://appshunter.io/ios/app/purr-machine/id6772356141) All apps by Mark Friedlander: https://appshunter.io/developer/1812095304 --- *Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-11.*