Memz LLM vs Radiant

Memz is your second brain — a private memory vault that lives entirely on your device. Capture anything in one tap: speak a thought and let on-device voice-to-text transcribe it, jot a note, save a photo, a screenshot, or a file. Memz reads and organizes it all into an evolving map of your memories — clusters that grow and reshape as you add more, with no manual filing. Then just ask. Memz recalls what you saved with answers grounded in your own sources, and shows the evidence behind every reply. When it doesn't actually have the answer, it tells you — instead of making something up. PRIVATE BY DESIGN - Everything stays on your phone. No account, no sign-up, works fully offline. - On-device processing — your memories are never required to leave your device. - Sensitive memories (Care and Secret) are locked behind an unlock step and kept out of everyday search. YOU OWN YOUR DATA - Export anytime to Obsidian-compatible Markdown. - Delete derived data only, or wipe everything — your call. WHAT YOU CAN CAPTURE - Voice notes with on-device transcription - Text notes and quick thoughts - Photos and screenshots, with on-device text recognition - Files and documents HOW MEMZ ORGANIZES - An evolving ontology groups related memories automatically - Review, merge, or split clusters as your thinking changes - A visual map shows how everything connects ASK YOUR MEMORY - Source-grounded recall with evidence for every answer - Scope your question; private categories stay excluded by default - No evidence, no guess — Memz refuses rather than inventing No subscriptions required. No data harvesting. Just your memory — organized, private, and yours.

Radiant runs open-weight models directly on your iPhone. Download a model once and it works anywhere — on a plane, underground, with no signal at all. Nothing you send it leaves the device, because there is nowhere for it to go: no account, no sign-in, and no server of ours in between. CHOOSE FROM 53 MODELS Models from Google, Meta, Mistral, Microsoft, IBM, Alibaba, NVIDIA, DeepSeek, Liquid AI, Hugging Face and more — grouped by who made them, from 0.2 GB up. Every model is labeled for YOUR iPhone before you download it: Runs well, Runs tight, or Won't run. That verdict is measured against the memory iOS actually grants an app on your specific device, not a guess from the spec sheet — so you know before you spend the download. BUILT FOR THE PHONE · Conversations are kept and named, so you can pick one up later · Switch models mid-conversation without losing what you were saying · Twelve color themes, four appearance modes, and your own text size · Full Dynamic Type and VoiceOver support BRING YOUR OWN KEY, OPTIONALLY If you want a model too large for any phone, add your own API key for Anthropic, OpenAI, OpenRouter, xAI, Nous, DeepSeek, Kimi, GLM, Groq or Mistral. Keys are held in the iOS Keychain. The line under every chat title tells you which model is answering and where it runs, so you always know whether you are on-device or online. Radiant is a Templeton Technologies product.