Privacy AI: Powerful AI client 16+

A Client for Local & Remote AI

AcmeUp Inc.

Designed for iPad

    • Free
    • Offers In-App Purchases

Screenshots

Description

It supports GGUF & MLX models or connect to OpenAI-compatible servers. Free Plan includes most features like local models, iCloud Sync, Markdown conversion and 25+ tools.

Privacy AI offers a Free Plan. Most features such as local models, Apple on-device model, iCloud sync, Markdown conversion, and 25+ built-in tools, are free. Only Cloud models, MCP, and custom API providers require a subscription.

Privacy AI is a full-featured AI chat client that works the way you choose: run models fully offline, connect to your self-hosted servers, or use cloud providers. All in one app.

Why Privacy AI
Most AI apps lock you into a single service. Privacy AI is different. It gives you freedom: local execution for privacy, self-hosted for compliance, or cloud APIs for top performance. You decide where models run and how your data is handled.

Who It’s For
• Developers and infra builders (GGUF, MLX, OpenRouter, or custom APIs)
• Privacy-conscious professionals in law, healthcare, finance, research
• Power users exploring automation and model performance
• Enterprises needing compliance or internal-only workflows

What It Does
Run Any Model, Anywhere
• Execute models fully offline on iPhone, iPad, or Mac
• Load GGUF or MLX models from HuggingFace or local files via iCloud
• Connect to OpenAI, Anthropic, Gemini, DeepSeek, or your own (Ollama, LM Studio, vLLM, LocalAI, Jan AI, OpenRouter)
• Switch between local and remote models mid-chat without losing context
• Supports Apple’s on-device Foundation Model in iOS 26

Use Tools Seamlessly
• Full MCP support
• Call tools like search, stocks, arXiv, HealthKit, JavaScript—even offline
• Inspect tool execution with built-in dev tools
• Tool calls in chat are saved and reloaded with history

Automate Anything, Privately
• Trigger workflows with Siri, Shortcuts, or Share Extension
• Send emails, analyze health data, summarize PDFs—no server required
• Offline TTS with pause/resume, plus transcription
• Supports OpenAI protocol TTS (gpt-4o-tts, gpt-4o-mini-tts)

Process Files On-Device
• Handle multiple attachments or URLs in one chat
• Convert PDFs, Office docs, EPUB, HTML, YouTube, audio
• Import media with smart resizing, OCR, and Markdown conversion
• Paste or drag images, videos, or files from clipboard directly into chat
• Export to Markdown, PDF, HTML, EPUB, or JSON

Images & Editing
• Generate images locally or via OpenRouter (Gemini 2.5 Flash supported)
• Support for gpt-image-1 and HuggingFace’s FLUX.1-dev models
• Rotate, zoom, flip, or edit AI images interactively
• Draw/annotate with Apple Pencil or touch

Control & Extend
• Hands-free “Natural Talk” voice UI
• Edit sent messages with attachments preserved
• Live context usage indicator
• Customize prompts, tools, and preferences
• iCloud sync for models, chats, and settings

Track Costs
• Fetch latest pricing from providers
• Compare and choose the most efficient model

Built for Apple Ecosystem
• Optimized for M-series Macs and iPad Pro
• Requires iOS 18.6+, aligned with latest Apple API standards
• iCloud native: models, chats, and settings sync automatically
• Reader: capture photos and smarter JS handling
• Siri + Shortcuts: run tools by voice
• Share Extension: send files or pages from Safari, Mail, or Files

No Account. No Surprises.
Privacy AI never forces you to sign up. You choose local, self-hosted, or cloud. Your data stays under your control.

It’s more than a chatbot—it’s a professional-grade AI IDE in your pocket.
Your model. Your device. Your data.

Welcome to the era of choice in AI.

Terms of Use: https://privacyai.acmeup.com/docs/policy/tos.html
Privacy Policy: https://privacyai.acmeup.com/docs/policy/privacy.html

What’s New

Version 1.3.2

Features
- MLX Model Integration
Privacy AI now supports the MLX model engine, enabling both text and vision models to run locally. You can directly download models from Hugging Face by entering a repository ID and access token (if required).
The new download manager adds resume-on-failure, background downloading, and a model integrity verifier for reliable large-model transfers.
MLX models now fully support local tool calls and MCP tool calls, just like GGUF and remote API models.
Best of all, MLX model support is included in the Free Plan.
- Clipboard and Drag-and-Drop Enhancements
The Chat and Reader editors now allow pasting images, videos, and files directly from the clipboard. On iPad, you can also drag and drop files or images into the chat editor — a smoother, more natural way to attach media.

Improvements
- llama.cpp Upgrade
Updated llama.cpp from b6558 → b6692, adding compatibility for new models such as Qwen3 Reranker and LiquidAI LFM2-2.6B, plus broader quantization format support.
- Text Rendering Refinement
Improved text layout and rendering during “thinking” mode for better readability and consistency across devices.
- Smarter Model Switching
Switching local models now filters to show only models of the same type — MLX, GGUF, or Apple Intelligence — for a cleaner experience.

Bug Fixes
- Thinking Text Display
Fixed an issue where “thinking” models occasionally displayed incomplete or cut-off lines when collapsed.
- Thinking Mode Persistence
Fixed a bug where the local model’s thinking-mode setting was not properly saved or applied to new chat sessions.
- Single Local Model Enforcement
Resolved a critical issue where MLX and GGUF models could run simultaneously, potentially causing memory overflow.

App Privacy

The developer, AcmeUp Inc., indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy.

Data Used to Track You

The following data may be used to track you across apps and websites owned by other companies:

  • Identifiers
  • Usage Data

Data Not Linked to You

The following data may be collected but it is not linked to your identity:

  • Identifiers
  • Usage Data

Privacy practices may vary based on, for example, the features you use or your age. Learn More

You Might Also Like

ReactorAI
Productivity
microAI
Productivity
Serval: Finest Ollama Client
Productivity
Morphix AI - Create Your Apps
Productivity
LLM Pigeon
Productivity
Local LLM: MITHRIL
Productivity