Offline AI Chat: MemoryAI

Content rating
Teen
5K+
Downloads
Content rating
Teen
Diverse Content: Discretion Advised
Learn more
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image

About this app

MemoryAI — an AI assistant that lives on your phone and works without internet.

• Ask questions, write, and summarise your documents — by typing, or by talking hands-free
• Your chats stay on your phone: no account, no ads, no subscription
• Kid Mode with parental controls: a PIN, a content filter and a locked model

Download one AI model once (0.3–4 GB, best over Wi-Fi), then use it anywhere: on a plane, abroad, with no signal. Works on devices with 4 GB+ RAM.

🔒 Complete Privacy
Run powerful AI models directly on your phone. Your conversations, documents and memories stay on your device: no AI servers, no login required. The app sends only anonymous diagnostics and usage data, never the content of your chats.

🧠 AI Features
• Chat with AI — multi-turn conversations that keep the whole chat in context, up to the model's limit
• Agent Memory (optional) — turn it on in Settings and the AI remembers what you tell it, in your own words, stored locally on your device; view, edit or delete memories any time. Requires an embedding model
• Chat Search — search and filter your conversations by title or message
• Continuous Voice Mode — fully hands-free: speak naturally, and the AI listens, responds, and speaks back without tapping
• Voice Input — speak instead of typing with on-device transcription
• Text-to-Speech — listen to AI responses read aloud, or enable auto-speak for hands-free use
• Document Analysis (RAG) — import PDF, TXT and MD files and ask questions about them
• Image Understanding — analyze photos with Vision AI models; select multiple images at once
• Chat Templates — 20 pre-built AI personas (code helper, writing coach, tutor, and more)
• Benchmarking — measure model speed (tokens/sec) directly on your device
• Context Window Display — see current vs. max token usage, so you never exceed the model's limit

🔧 Power User Features
• Import custom GGUF models — bring any compatible model from HuggingFace
• Dual engine — Gemma (MediaPipe / LiteRT) + llama.cpp; choose the backend that fits your needs
• HuggingFace Token Management — save and manage your token for seamless gated model downloads
• Model parameters — adjust temperature, top-k, top-p, max tokens per model
• Pause & Resume Downloads — control large model downloads to save data or battery
• Backup & Restore — save your chats and settings to Google Drive

👨‍👩‍👧 Kid / Safe Mode
• PIN-protected parental controls
• Content filter blocks inappropriate words before they reach the AI
• Model Safety Checks — automatic warnings to prevent unverified imported models from running in Kid Mode
• Locks the active model — child cannot switch or change settings
• Age-appropriate AI responses, guided by a safety prompt
• Parental Unlock — temporarily access settings and documents from the chat screen without disabling Kid Mode

📱 Works Everywhere
• Android
• 10+ AI models: Gemma, Llama, Phi, Qwen, DeepSeek, and more
• Available in 6 languages: English, Italian, German, French, Spanish, Portuguese

💎 Completely Free
• Unlimited chat, voice, vision, documents, image OCR
• Documents: PDF, TXT, MD and images (JPG, PNG)
• No ads, no subscriptions, no in-app purchases

Built by Facchinits — privacy-first AI for everyone.
Private offline chatbot, a local LLM on your phone. No internet, no account.
Updated on
Nov 4, 2026

Data safety

Safety starts with understanding how developers collect and share your data. Data privacy and security practices may vary based on your use, region, and age. The developer provided this information and may update it over time.
  • No data shared with third parties
    Learn more about how developers declare sharing
  • This app may collect these data types
    App info and performance and Device or other IDs
  • Data is encrypted in transit

What’s new

• Tools: a plain sum or a question about today's date is answered exactly, in your language, in an instant.
• A Thinking switch in Model Parameters for the models that reason: off, answers come in seconds.
• Backup: no size limit in memory, sizes in KB, iCloud upload confirmed.
• The model page keeps its Download or Delete button in view.
• A model that crashed the app is not loaded again by itself; on 3–4 GB phones hopeless loads are refused with the figures; imported models say why they fail.