LLMster vs MakeYour

Local AI, in your pocket. LLMster is a fast, private iPhone and iPad client for models running on your LM Studio server. Stream replies, reasoning, tool activity, and image-based conversations from the models you host—in an app designed to feel at home on iOS. Private by design LLMster connects directly to the server you choose. There’s no LLMster account, telemetry, hosted chat service, or cloud relay in the middle. Your conversation library stays on your device, while model context stays with your configured server. External integrations run only when you choose to enable them. Your models, wherever you run them Keep your models on the machine built for them: a workstation, home server, or always-on computer. Run the LM Studio desktop app or LM Studio’s headless daemon, point LLMster at the host, and start chatting. No companion desktop client is required. Choose the right model without leaving the conversation: • Search or sort by name, size, or format, then pin favorites • See which models support vision, reasoning, or tool calls • Change models without starting a new chat Organized from the start Search chats by title, model, or folder. Browse recent conversations across every folder, then organize, rename, pin, or duplicate important threads. Move and protect your chats Share individual conversations as .llmster files and import them on another device while preserving messages, images, reasoning, tool history, and chat settings. Back up and restore your entire local chat library—including folders, pins, drafts, and attachments—with optional password protection. Backups do not include server addresses, authentication keys, or app-wide settings. LLMster also verifies transferred response context against your configured LM Studio server before continuing a chat. Vision, direct to your server Attach up to four screenshots, photos, or scanned pages to a message and send them to a compatible vision model. LLMster resizes and compresses images on your device before sending them, so the originals remain with you. Open any attachment and pinch to zoom when you need to inspect the details. Hands-free voice chat Talk naturally using on-device speech recognition and text-to-speech. Audio stays on your device; only the resulting text is sent to your configured server. Natural turn-taking and subtle haptics keep the conversation moving without touching the screen. Control each conversation Every chat can have its own: • Integrations already configured in LM Studio • Custom system prompt • Tool-call visibility • Live reasoning preference Stream reasoning as Markdown while the model works, or keep the interface quiet with a compact Thinking indicator and open the completed reasoning when you want it. Control response auto-scrolling, and choose System, Light, or Dark appearance with your preferred accent color. Rich responses, as they arrive LLMster renders streaming Markdown smoothly, including syntax-highlighted code with copy controls, inline and block math, tables, links, lists, and more. Export or share transcripts with their original Markdown intact. Keep going while you move on LLMster asks iOS to continue eligible responses after you leave the app. When the system starts continued processing, progress appears as a Live Activity on the Lock Screen and, on supported iPhones, in the Dynamic Island. When a background response completes, LLMster can notify you locally—without routing your conversation through a push server. Tap a notification or Live Activity to return to the correct conversation. Setup instructions are available at https://llmster.app/support

Stop downloading another tiny app. Make yours. MakeYour turns a sentence into a native tiny app inside one trusted iPhone app. Build trackers, checklists, calculators, reminder workflows, photo journals, live-data dashboards, ledgers, or games—then keep and switch among them. WHAT YOU CAN BUILD • Personal record collections with notes, numbers, dates, totals, completion, and reminders • Task lists and local notification workflows • Calculators and currency-conversion tools • Credited BBC/NPR news collections with local search, topics, and bookmarks • Stock and ETF watchlists with latest/delayed Twelve Data quotes and charts • Income and expense ledgers with balances, budgets, and category totals • Complete original platform and Snake games with touch controls and scoring • Photo-first private journals and trackers using selected or captured images • Latest daily FX watchlists with a chosen base currency, editable currencies, and threshold alerts • Tap-initiated camera, QR/barcode/text scanning, one-time location, contact and text-file selection, today's steps, sharing, clipboard write, and haptic feedback • Local voice notes with optional on-device-only transcription, editable review, and no network-recognition fallback • Explicitly opted-in tiny apps that open from Apple Shortcuts or Siri through one authenticated foreground action • Focused AI helpers that receive only text you explicitly review and send YOUR STYLE, NOT ONE TEMPLATE Generated apps can use different native themes, typography, backgrounds, layouts, spacing, surfaces, imagery, symbols, and colors while remaining accessible and familiar. BRING YOUR OWN OPENAI KEY Your API key is stored in iOS Keychain for this device only. AI requests travel directly from your iPhone to OpenAI. MakeYour does not operate an account or proxy server and never puts your key in a project file or prompt. Market Pocket includes AAPL demo access. Other symbols can use an optional Twelve Data key stored in the device-only Keychain. PRIVATE BY DESIGN Projects, records, bookmarks, watchlists, ledgers, voice notes, accepted transcripts, and selected or captured results stay on your iPhone. Device access starts only after you tap, scanned URLs are not opened automatically, and there is no background audio, speech, location, or motion monitoring. Speech transcription requires an available on-device language model and never falls back to network recognition. Sharing leaves MakeYour only after you choose a destination in Apple's share sheet. Before an in-app AI request, MakeYour shows the exact task and text that will be sent. An accepted transcript may become editable text, but its audio is never attached. Photos, records, other apps, and device data are not attached automatically. When generated versions include the visible Shortcuts access block, Apple's dynamic picker receives only opted-in tiny apps' stable IDs, display names, and validated icons. The fixed action requires local device authentication and opens MakeYour in the foreground. It receives no prompt, state, photos, voice notes, provider keys, or generated automation code. Removing the block or deleting a tiny app revokes that app's listing. SAFE NATIVE RUNTIME AI does not download or execute Swift, JavaScript, plug-ins, or arbitrary code. It creates a validated declarative app document. MakeYour renders that document using precompiled native SwiftUI components and a fixed capability allowlist. Network components use only fixed, precompiled providers: Frankfurter for latest daily FX reference rates, BBC/NPR for credited RSS feeds, Twelve Data for latest/delayed market data, and OpenAI for user-authorized AI. Market and currency values are not guaranteed real-time and are not financial advice. Camera capture, live scanning, pedometer data, and meaningful haptic feedback require supported physical iPhone hardware. Unsupported devices and Simulator show an honest unavailable state.