# Open Minis — Your Private On-Device Agent > On-device AI agent for task automation and iOS integration. (iPhone/iPad app by 森 王.) - Source: https://appshunter.io/ios/app/open-minis/id6759188481 (this page in markdown: same URL + `.md`) - Developer: [森 王](https://appshunter.io/developer/1522405790) - Category: Productivity, Utilities - Price: Free - Rating: 4.90/5 from 68 App Store ratings · 59 written reviews indexed - Age rating: 17+ - Requires: iOS 16.0 · 124 MB - Languages: Russian, American English, European Spanish, Korean, German (Germany), Chinese (Traditional, Taiwan), Chinese (Simplified, China), French (France), Japanese - Released: 2026-03-14 - Data updated: 2026-09-09 - Monetization: free - User reviews in markdown: https://appshunter.io/ios/app/open-minis/id6759188481/reviews.md ## What is Open Minis? Minis — Local-First On-Device AI Agent Minis is a local-first, on-device AI agent that goes beyond chat. All your data stays on your iPhone — nothing is uploaded to a server by default. Running locally means lower latency and stronger privacy, while the agent still takes real action: browsing the web, accessing your health data, managing your schedule, controlling your smart home, and automating complex tasks. Local-First AI Agent Unlike cloud-only chatbots, Minis runs directly on your device and keeps your data there. The agent executes multi-step tasks autonomously, using tools and native iOS frameworks to get things done — not just answer questions, and not just relay everything to the cloud. Multi-Model, Your Choice Bring your own API key. Choose from leading AI providers: • Anthropic Claude • OpenAI GPT • Google Gemini • DeepSeek • Kimi (Moonshot AI) • OpenRouter • Any OpenAI-compatible endpoint Deep iOS Integration The agent accesses Apple frameworks natively: • HealthKit — steps, heart rate, sleep, workouts, SpO₂ • Calendar & Reminders — create events, check availability, manage tasks • HomeKit — control lights, switches, scenes, and smart accessories • Photos — search, organize, and export from your library • Location & Maps — current location, directions, nearby POIs • Vision — OCR text recognition, object detection, barcode scanning • Speech — real-time transcription and text-to-speech • Weather — current conditions, hourly and daily forecasts Built-in Web Browser Navigate pages, take screenshots, extract content, fill forms, and interact with websites — all driven by the AI agent in the background. Skills System Import or create custom AI skills to extend the agent's capabilities. Share skills with others or build your own for specialized workflows. Persistent Memory The agent remembers your preferences, project context, and recurring patterns across sessions — building a personalized assistant that improves over time, all stored locally on your device. Siri Shortcuts Automate AI tasks with Siri and the Shortcuts app. Send prompts with file attachments, wait for results, and chain into complex workflows — all hands-free. Privacy by Design Your API keys and data stay on-device. Fine-grained permission controls let you decide exactly which personal data the agent can access. No account required. No data collected. ## Key features - On-device AI agent - Multi-model AI provider support - Deep iOS framework integration - Built-in web browser - Customizable skills system - Persistent memory - Siri Shortcuts integration ## Recent user reviews (10 of 59) All indexed reviews: https://appshunter.io/ios/app/open-minis/id6759188481/reviews.md ### 4/5 — Vietnamese *2026-08-31* Please add Vietnamese language support. ### 5/5 — 加油 *2026-08-31* 不错 ### 5/5 — The best app ever *2026-08-29* Honestly, this app is incredible, A sleek and clean user-friendly interface. Really smooth performance. So useful features and tools. All functions make customization incredibly seamless. (and It would be great to see github copilot on the provider list). Please consider adding Arabic language support in the upcoming updates and it will be 10/10 (Keep up the great work) ### 5/5 — 好用，很智能 *2026-08-28* 👌 ### 4/5 — 不停闪退 *2026-08-18* 为啥我用了两天，不停得闪退，闪退的快用不成了 ### 5/5 — Incredible! But after updating some providers report bad request, wish to fix it *2026-08-18* After updating to the latest build, Minis automatically injects the prompt_cache_key parameter into outgoing API request. Some strict OpenAI‑compatible backend services do not recognize this parameter. These backends will reject requests and return HTTP 400 Bad Request **Developer response:** Thanks so much for the kind words, and sorry for the trouble! This is a known issue with the auto-injected prompt_cache_key parameter breaking some strict OpenAI-compatible backends - it's already fixed in our latest TestFlight build. Please join TestFlight to get the update: https://testflight.apple.com/join/3BdkA5c3 ### 5/5 — 巨好用 *2026-08-17* 夯爆了 ### 5/5 — Шикарная работа *2026-08-16* Ждём обновлений ### 4/5 — 整体相当好，但是存在不足 *2026-08-15* App 内置的 minis-mcp-cli call 命令，在调用 HTTP 类型的 MCP 服务器时，无法正确解析 imageFileUri 等必需参数，无论是传 --param 还是 JSON 字符串，都报 PARSE_ERROR 和 alive: false，请修复。目前本地 Apple Vision 正常。 其他对于设备端的体验和集成相当好 ### 5/5 — 感觉比苹果自带ai好用 *2026-08-12* 试过美版的ai，没啥大用，说实话没有这个可玩性高。 ## Frequently asked questions about Open Minis ### What AI models can I use with Open Minis? Open Minis supports multiple AI models, allowing you to bring your own API keys. You can choose from leading providers such as Anthropic Claude, OpenAI GPT, Google Gemini, OpenRouter, and any OpenAI-compatible endpoint. ### How does Open Minis integrate with my iPhone? Open Minis deeply integrates with native iOS frameworks. It can access HealthKit for health data, Calendar & Reminders for scheduling, HomeKit for smart home control, Photos for library management, Location & Maps for navigation, and Vision for OCR and scanning. ### Can Open Minis automate complex tasks? Yes, Open Minis is designed to execute multi-step tasks autonomously. It uses tools and native iOS frameworks to get things done, going beyond simple chat responses. You can also import or create custom AI skills to extend its capabilities. ### Is Open Minis private and secure? Open Minis is built with privacy in mind, running entirely on your device. Your API keys stay local, and you have fine-grained permission controls over personal data access. No account is required, and no data is collected. ### How does Open Minis remember my preferences? The agent features persistent memory, allowing it to remember your preferences, project context, and recurring patterns across sessions. This helps it build a personalized assistant that improves over time. ### Can I control Open Minis with my voice? Yes, Open Minis integrates with Siri Shortcuts. You can automate AI tasks hands-free by sending prompts with file attachments, waiting for results, and chaining them into complex workflows through the Shortcuts app. ### What devices is Open Minis available on? Open Minis is available on iPhone and iPad devices. It requires iOS 17 or later and is rated for users aged 17 and up due to its advanced AI capabilities. ### How often is Open Minis updated? The latest version of Open Minis is 1.2, last updated on March 31, 2026. While specific update frequency isn't detailed, the app is actively maintained, with a recent update indicating ongoing development. ## Version history (last 5 releases) ### 1.13 — 2026-08-27 Minis (iOS) 1.13 New: Backup & Restore (Settings → Storage) Export your chats, provider configs, credentials, environment variables, custom thinking rules and shared files into an encrypted .minisbak package, and send it to Files, a network folder, or a remote server (S3, WebDAV, SFTP, SMB, FTP, etc). Restore opens from your configured destinations, lets you browse folders, shows download size and progress, and lets you cancel a slow package open or download. Name your device so backup packages are easier to identify and sort, and delete individual remote backups. Restore merges everything back safely, with automatic rollback if anything goes wrong. New: Personalize your assistant Choose an emoji or image as your assistant's identity icon. The icon appears consistently across chats, and tapping the assistant header opens Soul settings directly. New: Spanish language support Minis is now available in Spanish. Language changes apply throughout the app without requiring a restart. New: Improved accessibility Chat controls are labeled for VoiceOver, and Minis announces when an assistant response finishes. Also new - Third-party OpenAI/Anthropic-compatible providers can be added without an API key - The thinking toggle shows an icon with an "Off" label when disabled - Weather results include precipitation amount, wind gust and direction - Long-press a chat message for "Delete From Here" - Swipe left on a provider, model group, or backup destination to Edit or Delete - Transient provider errors now auto-retry with backoff - The About screen shows the build date next to the version number Bug Fixes - Fixed a file-permission check that could be bypassed under certain paths - Fixed crashes from malformed or mistyped custom provider Base URLs - Fixed math formulas being invisible in dark mode - Fixed shared-scope web apps rendering a black screen - Fixed conversations getting stuck after context compaction or an unanswered message - Fixed a rare crash from an out-of-range message index in long conversations - Fixed images and video thumbnails sometimes appearing squished on first load - Fixed the tool-call status losing its model-supplied title - Fixed the @-mention file list going stale after mounts or files changed - Fixed "Add to input" silently overwriting existing draft text - Fixed stale stream-stall errors, and mid-stream stalls not retrying automatically - Fixed the code-block copy button not responding on iOS 17 - Fixed the masked API key field not being tappable for editing - Fixed Gemini 3.7 Flash and Claude 5 rejecting the thinking-off setting - Fixed the browser automation tool hanging or returning unusable values - Fixed a background tool service exiting while still in use - Fixed shared content being lost or delayed when the target session wasn't active - Fixed paused-session badges being re-stamped or showing the wrong date - Fixed provider sync not repairing iCloud data divergence - Fixed a rare crash from re-laying-out a large Chinese/CJK document preview in the background - Fixed the session list showing a raw tool name instead of a readable summary - Fixed memory-heavy requests sometimes failing unexpectedly during long conversations - Fixed a broken local environment getting stuck instead of recovering automatically - Fixed long inline code in Markdown messages wrapping or highlighting incorrectly - Fixed audio files with no usable audio track failing after being sent to transcription - Fixed backup restore path handling and category counts in some cases - Fixed token usage sometimes being attributed to the wrong model - Improved performance of the provider list and long-conversation compaction - Improved stability of the built-in terminal ### 1.12 — 2026-08-18 Session Groups Group related sessions together in the session list, with a custom icon — either manually or by letting AI auto-classify them. Group cards surface member status alerts, and a mini-bar appears while scrolling through an expanded group so you can jump back to its header. Vision Input: image understanding for text-only models Models without native vision (like DeepSeek) can now "see" images. Minis asks a vision-capable model to describe the picture first, tells you which model did it, and reports clearly if that fallback fails. Custom Thinking Rules Providers now have a "Thinking Rules" section on their detail page — add, edit, delete, and reorder how reasoning parameters get sent per model. Rules sync via iCloud. Liquid Glass across the app On iOS 26, the home screen's floating buttons, the message composer, the tool-status bar, and sent messages all now use Liquid Glass instead of a solid background. Older iOS versions are unaffected. Kimi Code account sign-in Added the option to sign in with a Kimi Code account. Richer parameters for Apple tools Reminders now supports location-based alerts (on arrival/departure) and recurring rules. Notifications support repeating schedules and interactive action buttons. Weather adds minute-by-minute precipitation for the next hour. Reliability improvements Fixed a stuck iCloud sync migration that could show fake progress or never finish. Fixed thinking models stopping mid-stream during long responses. Fixed background tasks occasionally being interrupted by the system, and a rare crash when an external storage volume was mounted. Fixed a launch-crash loop so the app recovers instead of repeatedly crashing. Faster, more reliable prompt caching Fixed several issues that were preventing prompt caching from working as expected across multiple providers, and corrected a token-usage counting bug that could misreport cache hit rate and context usage. Bug Fixes - Fixes long text getting clipped or unscrollable when pasted into the composer - Fixes voice input/output issues, including muted read-aloud not resuming and dropped opening words in recordings - Fixes math formulas with superscripts and subscripts sometimes rendering as plain characters - Fixes provider names occasionally showing incorrectly on a model row - Fixes message bubble heights sometimes being measured inaccurately for image attachments - Fixes HealthKit queries sometimes silently reporting "no data" instead of the real error - Fixes the model list order and refreshes the Codex OAuth model list - Fixes Shortcuts automation notifications (duplicate alerts, missing prompts, permission prompts during a run) - Fixes "Move to…" sometimes losing shared content when the target session wasn't ready yet - Fixes a custom OpenAI-compatible provider rejecting requests over an unsupported field - Fixes several chat rendering issues, including blockquote nesting near images and stale layout heights in the footer area ### 1.11 — 2026-07-31 New: "Ask Minis" via Siri — say "Hey Siri, Ask Minis" to jump straight into a live conversation. New: Kimi Code sign-in support, plus full OAuth login for MCP servers (with iCloud config sync across devices). New: Codex Fast Mode toggle for OpenAI OAuth models. New: Live Activity (privacy mode) now shows real task progress — position, status, and run time. New: Select any text and tap "Read Aloud" to hear it via Minis TTS. Voice correction learning now uses real conversation context, further improving correction accuracy. New: Max output length raised from 64K to 128K tokens. In-browser downloads got a full UX overhaul with floating progress cards and a downloads panel. Stability: Fixed several stability issues in message streaming, Live Activity restore on iPad, HealthKit data reads, and config loading after a device restart. Reduced stutter during long "thinking" streams and scrolling. Bug fixes: - Markdown tables keep their scroll position while streaming - Fixed duplicate thinking bubbles on retry - Fixed invisible scroll buttons in light mode - Fixed navbar title staying blurred after Face ID unlock - Session list timestamps are properly localized - Fixed in-app browser fetch failures - Fixed Mistral chat compatibility issue - Backfilled translations for ~200 previously English-only strings - Added Claude Opus 5 to the built-in model list - Fixed occasional config or chat history issues after a device restart - Fixed occasional unresponsiveness when checking Now Playing info or using speech synthesis - Fixed regenerating a session title not following the latest model order - Fixed some health metric types occasionally being skipped when reading HealthKit data - Fixed onboarding setup steps missing translations in some languages - Reduced app install size ### 1.10 — 2026-07-25 Voice input & output On-device VAD recording with pluggable ASR/TTS providers (Azure, Doubao, Xiaomi MiMo, system online/offline), fail-over across providers, a redesigned voice panel, and an optional AI correction pass using recent conversation context. App Lock with Face ID Lock the entire app with Face ID, Touch ID, or passcode, with a configurable grace period and a privacy screen in the task switcher. model-use passthrough mode Command-line tool calls can now pass raw request bodies, headers, and custom endpoints straight through to a model provider, with warnings surfaced when fields are silently dropped or downgraded. Thinking level in the nav bar A badge to view and change a session's reasoning effort, with Max/Ultra tiers, a picker, and a slash-menu shortcut. Streaming rendering Messages glide into place with word-by-word fade-in; code blocks animate open as they stream. Model Quick Test Test a model's top-3 modalities concurrently, with results shown side by side. Live Activity Play/pause and mute/unmute narration from the Dynamic Island and Lock Screen; fixes stuck timers and stale state after a session finishes. Compact Messages A "Compact Messages" menu entry and a one-tap auto-compact option on the capacity warning. Also in this update - Long-press the new chat button to start a session with a specific model group - Azure OpenAI mode for OpenAI/Responses providers - Modality icons and priority tags on Model Groups - Editable Context Window for any model - Scroll-to-top button in long chats - Print support for web pages, images, Markdown, and text previews - Copy table as image - Session titles summarize both the first and last turns - Cache hit rate shown in the Token Usage sheet - Claude Sonnet 5 and GPT-5.6 (sol/terra/luna) added; Grok list synced - Multiple fixes to the built-in terminal, improving stability Bug Fixes - Fixes the "..." menu refreshing or resetting mid-streaming - Fixes context-window usage showing stale numbers after editing a model or model group - Fixes English text wrapping mid-word instead of at word boundaries - Fixes a bottom gap in the voice panel after edit-and-send - Fixes a 3-second UI freeze when switching from voice to text input - Fixes voice-template model sync deleting API-fetched audio models on launch - Fixes three app crashes caused by dangling view references - Fixes Markdown code block spacing inconsistencies - Fixes voice input panel gestures conflicting with transcript scrolling and editing - Fixes the chat input bar retaining stale height across re-entry - Fixes terminal crashing after a rootfs reset - Fixes silent playback in the System TTS/ASR path - Fixes thinking not disabled for adaptive-reasoning models set to "off" - Fixes Gemini models failing when a response contains an empty text segment during tool calls - Fixes reasoning mode not working for some third-party models - Fixes retried messages occasionally disappearing from chat history - Fixes Token Usage counting inaccuracies on reloaded sessions - Fixes a crash on iOS 26.5 caused by a removed WebView API - Fixes table columns collapsing or clipping emoji during streaming - Fixes Bluetooth keyboard send leaving the software keyboard on screen - Fixes a memory leak in iCloud sync's per-session cache - Fixes idle CPU sitting at 100% in the session list - Fixes a slow cold start when opening a session - Fixes main-thread hangs during long-message streaming ### 1.9 — 2026-06-23 What's New 1. MCP Integrations — Connect Any Tool to Your AI Minis now supports the Model Context Protocol (MCP), letting you connect external tools and services directly into the agent loop. Add MCP servers via Settings → MCP Integrations, import configs from JSON, or manage them from the shell with the new  minis-mcp-cli  command. 2. SOUL Personality Customize your AI's personality — name, style, language, and character — directly in Settings. Everything is saved to SOUL.md and persists across sessions. The sidebar title, default session name, and typing indicator all reflect your Soul's name. 3. iCloud Sync V2 Upgraded to record-level sync. Providers, Model Groups, and environment variables now sync independently per entry. Fixes issues where deleted configs were resurrected by iCloud, local API keys were overwritten on merge, and active sessions had their content overwritten mid-run. 4. Providers OpenAI: Generate images directly in chat using gpt-image-2 via OpenAI OAuth / Codex instances. New xAI provider with one-tap SuperGrok / X Premium+ login. 5. Memory Toggle A new global memory toggle in Settings controls whether new sessions enable memory by default. Turning it off fully suppresses memory injection and hides memory tools. 6. Tool Calls The agent loop now dispatches multiple tool calls in parallel, making multi-step tasks significantly faster. Long-press any tool capsule to re-run from that exact point, or copy the tool call details. Bug Fixes • Fixed multiple chat crashes including session switch UAF, notification deeplink wake, and iPad sidebar collapse jank. • Fixed generated content being lost after Stop or Retry. • Fixed vision models not seeing images returned by read_image or browser_use. • Fixed concurrent browser_use calls trampling the same WebView across tabs. • Fixed Codex OAuth non-streaming calls triggering HTTP 400 Stream must be set to true. • Fixed orphaned tool_use and tool_result blocks being sent in Anthropic requests. • Fixed reasoning models returning empty text when generating session titles. • Fixed slash menu disappearing in over-input mode and installed Skills not appearing in the list. • Fixed token counts being inflated by providers that report cumulative usage on every SSE chunk. • Fixed compact running in an infinite loop. • Fixed image generation requests timing out at around 120 seconds. • Fixed camera captures being stored as oversized lossless PNGs. ## More apps by 森 王 - [Scrcpy Remote](https://appshunter.io/ios/app/scrcpy-remote/id1629352527) All apps by 森 王: https://appshunter.io/developer/1522405790 ## Related topics [kuikoto](https://appshunter.io/ios/topics/kuikoto) · [local ai agent](https://appshunter.io/ios/topics/local-ai-agent) · [open doors ai](https://appshunter.io/ios/topics/open-doors-ai) --- *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 2026-09-09.*