miniAssistant vs LLMster

* Works with the LM Studio API, OpenAI API, Anthropic API, and Apple Intelligence! * Try large language models (LLMs) on your iPhone, iPad, or Mac. * Choose your preferred language model from LM Studio / OpenAI / Anthropic / Apple Intelligence. * The LM Studio tab connects to any OpenAI-compatible server, so you can point it at your own setup. * Each provider is tuned individually, including a high precision mode you can switch on. * Personalize the prompt to tailor the app to your own needs. * Function calling is available for calendar events, reminders, notifications, web search and page fetching, location data, on-device memory, knowledge base search, image generation, and user interaction. * Summarize, create, and edit your schedule in natural language. * Keep short notes on your device and let the AI recall them in later conversations. * Add your own documents and let the AI search them on your device by meaning, not just by keyword. * Review the whole conversation at any time from the history button. * Change the background using images from your photo library. By default, the app opens the conversation by listing today's remaining calendar events — or tomorrow's, if none are left. It can do this because it reads the calendars, reminders, location, and current date on your device. You can instruct the LLM in natural language, for example: "if WWDC is not in June, look up the date and add it to my calendar". You can even ask local LLMs about the weather forecast or the latest news. The app automatically replies in your device's language. [Note] * This app is provided free of charge for research purposes. * Use it at your own risk, and do not rely on it for critical or high-stakes decisions. * The current time on your device is sent as the initial user prompt, and your device's language setting is sent as the system prompt. * When function calling is enabled, the app sends data from your device to the AI you selected. This may include calendar events, reminders, location data, saved notes, and excerpts from documents you have added to the knowledge base. * Image generation is available with OpenAI models only. * API usage fees apply when you use OpenAI or Anthropic models with your own API key. * The software is provided "as is," and the author assumes no responsibility for its performance. * This app is a technical demonstration of LLM usage and should not be used for critical decisions, including business or medical purposes. * The content of AI-generated responses depends on the model you select. * AI may generate incorrect responses, and their accuracy is not guaranteed. [Safety Measures] * You are asked to confirm after every five consecutive function calls. * Function calling always stops after twenty consecutive calls, and the AI answers with the information gathered so far. * In Safe Mode, adding or editing a calendar event requires your confirmation through the standard iOS interface. * Deleting a calendar event always requires your confirmation, whether or not Safe Mode is enabled. * Location access is managed by the standard iOS permission system, and only approximate location data is used. * Saved notes and knowledge base documents stay on your device; only the passages that match your question are sent to the AI. [Apple Intelligence Limitations] * Requires an Apple Intelligence–compatible device running iOS 26 or later. * Limited context window: enabling many tools can exceed it, causing the model to skip tool calls and hallucinate. Disable tools you don't need. * Tool results are truncated to 1,000 characters, and earlier tool results are dropped in long conversations. * Reminders, memory, and image generation are not supported. * Safe Mode is always on. * Tool calling stops with an error after 20 consecutive calls.

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