LMSA for LM Studio & Ollama

TechMitten LLC

Contains adsIn-app purchases

About this app

LMSA – Private AI Chat App: Local LLM, Voice Chat, Ollama, LM Studio & OpenRouter for Android

Turn your Android phone or tablet into a powerful, private AI assistant. LMSA is a local LLM chat app and voice assistant that connects to on-device AI servers like LM Studio and Ollama, or cloud models via OpenRouter — so you can chat or talk with the world's best AI chatbots privately, securely, and completely on your terms.

Run DeepSeek, Llama 3, Mistral, Phi, Qwen, Claude, or Gemini — LMSA is the fastest, cleanest, and most private way to use AI on Android, whether you want a fully offline AI chatbot or instant access to cloud LLMs.

🔒 PRIVATE AI CHAT & VOICE ASSISTANT — YOU ARE IN CONTROL

On-Device Encryption: Your local chat database is fully encrypted on your device for total privacy.
Privacy First: No message tracking, ever. All chats are stored locally on your device.

Local-First AI: Conversations stay on your device and local network — true offline AI.

Private Voice Chat: Talk to your AI and hear it reply, with every expressive voice included for free. Speech recognition and text-to-speech run entirely on-device, so your voice audio is never uploaded or stored remotely — with local models or OpenRouter.

Direct Cloud Access: OpenRouter requests go straight to the provider — no middleman servers.

Biometric Lock: Secure your AI chats with fingerprint or face unlock.

🆓 FREE FEATURES INCLUDE:

Unlimited Chat: No daily limits on core conversations with your local or cloud LLM.

Local & Cloud Backends: Connect easily to Ollama, LM Studio, or OpenRouter.
Custom Endpoint Support: Connect directly to any compatible AI server.
Core Web Search: 2 live web searches per day for up-to-date answers.
File Attachments & Text-to-Speech: Feed documents locally and listen to AI responses.

Full Voice Chat: Speak to any connected LLM and hear it respond, with all natural voices unlocked and processed on-device — free for every user.
Auto Discovery: Scan your local network to find your AI server automatically.

👑 LMSA PREMIUM (ONE-TIME LIFETIME LICENSE, NO SUBSCRIPTION)

🎨 Unlimited AI Image Generation: Use the /image prefix directly in chat.
🌐 Unlimited Brave Web Search: Real-time news and up-to-date information.
🎛️ Full Parameter & Context Control: Custom system prompts, adjustable max tokens.
🚀 Save Custom Endpoints: Switch between multiple AI server profiles instantly.
👥 Templates & Personas: Build and chat with custom AI characters.
📥 Import/Export Chats: Back up and move your local conversation history.
🔌 True Offline Mode: Run completely offline with local models on your trusted network.
🚫 Ad-Free Experience & Premium Support: Priority email assistance, zero distractions.

🤖 COMPATIBLE WITH LEADING LLMs

Full support for GGUF models on LM Studio (PC/Mac).
Full support for Ollama servers and compatible open-source models.
Instant access to 100+ cloud LLMs via OpenRouter with your API key.
Thinking Mode: See the full reasoning chain for models like DeepSeek-R1.

🛠️ EASY SETUP IN MINUTES
Local AI (LM Studio / Ollama):

Install LM Studio or Ollama on your PC or Mac.
Load a model and start the local server.
Connect your phone to the same Wi-Fi network.
Enter the server IP and port in LMSA — start chatting.

Cloud AI (OpenRouter):

Get an OpenRouter API key at openrouter.ai.
Enter your key in LMSA settings and start chatting instantly.

🧑‍💻 PERFECT FOR:

AI enthusiasts experimenting with local language models
Privacy-focused users who refuse to send data to big tech
Developers, researchers, and power users building custom AI workflows

📋 REQUIREMENTS:

Android 6.0 or higher
LM Studio/Ollama on PC/Mac (same Wi-Fi) OR an OpenRouter API key

⚠️ Notice: LMSA is an independent app, not affiliated with LM Studio, Ollama, or OpenRouter. Some features are available to premium lifetime license holders only.

Ratings and reviews

Pretty good overall. Better than most. Good tools integration.A few things: - Whatever it is sending for thinking mode is driving qwen (3/3.5) insane. Goes on and.on with "wait, I should" for dozens of sentences before finally selecting a reply. Something I don't see from other clients - UI has a few odd quirks still, like wanting to be completely full screen - For a premium app I would like to be able to control morez like controlling the thinking budget, see more about what is being sent.

Promising but disappointed. The interface is pretty ugly but on paper it has everything I need, I can connect to my local LM Studio server and set up the MCPs. In practice though, the API token of all things isn't being sent correctly so I can't use it at all. I was trying Off Grid which has its own problems like not being able to use MCP servers on my PC, but I'd say this issue is worse because without a token I can't use the MCP servers anyways.

good app, does what it says on the tin. the UX needs some TLC (creating custom templates, preventing the new line button from sending messages, making the popup confirming the model is loaded show up less often/ less intrusively) but the foundation is rock solid. The cost to remove ads is extremely cheap, making this a solid all- rounder. looking forward to future updates!

What’s new

Resolved an issue where voice mode incorrectly reported active speech when no audio was ready for processing.