
Private Mind is an AI assistant that runs on iOS and Android, with conversations and document processing kept on your phone. It's for people who want private mobile chat, help reading files, or an assistant they can use without connectivity. It doesn't require an account. Models download from Hugging Face before use; after that, every feature works offline.
You can ask questions about PDF, TXT, Markdown, HTML and CSV files. The app finds relevant passages and creates embeddings on-device, and its answers link back to the text they draw on. That makes it easier to check a summary or see where an answer came from without sending the document to a cloud service.
Voice input also stays local: on-device speech recognition turns dictation into chat messages. You can send photos to a vision-capable model, too. Support depends on the model you choose.
Private Mind lets you choose a supported model or add your own, with support for custom models exported to ExecuTorch. Reusable system prompts let you shape responses for tasks such as studying, writing or coding, and you can adjust behavior for each chat. Conversation branching lets you explore a different answer from any message while keeping the original thread.
Built-in benchmarks compare model speed, performance and memory use on your own phone. The app uses Software Mansion's React Native ExecuTorch and React Native RAG technologies to run models and document retrieval on-device.
Claim this page with an email at privatemind.swmansion.com. Private Mind gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Private Mind?Promote it
Something wrong or outdated on this page?
3.2KUpdated 6 days agoMIT
macOS · Windows · Linux · iOS · Android#GGUF#Human approval#LM Studio integration
Off Grid AI runs language models on iOS, Android, macOS, Windows and Linux. You can chat, analyze documents and generate images on your own hardware. The mobile app uses the MIT license, while the desktop app uses AGPL.
llm.chinesepowered.comChat With Your Documents
iOS · Android#GGUF#Hugging Face integration#llama.cpp backend
noemaai.comChat With Your Documents
macOS · iOS#GGUF#MCP#MLX
20Updated 2 days agoAGPL-3.0
Android#GGUF#Hugging Face integration#llama.cpp backend
enclaveai.appChat With Your Documents
macOS · iOS#Works offline
Enclave AI runs downloaded language models on iPhone, iPad and Mac for text chat, voice conversations and questions about documents. Local processing works offline after the app and models are downloaded. The current App Store listing requires iOS or iPadOS 27, or macOS 27 on an Apple silicon Mac.
24.8KUpdated 23 hours agoApache-2.0
iOS · Android#Agent Skills#Hugging Face integration#Multilingual
Personal LLM runs AI chat, photo analysis and document questions on your phone, with no account or cloud inference. It's for people who want a private ChatGPT alternative on iOS or Android, including when they don't have a connection. Once you've downloaded a model and any image support files, those features work offline.
Noema is a private local AI assistant for iPhone, iPad, Mac, and Vision Pro. It's for people who want to chat with models and work with their own files on Apple hardware without depending on a cloud service. Local chats can stay on your device, and file retrieval runs there too.
CloverPal is an Android app for people who want private AI chat and character roleplay on their phone. Its Offline Silly Tavern mode lets you create characters with their own avatars and system prompts, then have them converse in group chats. Model inference runs on-device, and chats and uploaded files stay on your phone.
Google AI Edge Gallery is an open-source app for people who want to try generative AI on their own phone. It runs model inference locally, so offline chat, image analysis and audio tasks don't send your inputs to a server. It supports Android and iOS and uses the Apache 2.0 license.