off-grid-ai/OGAM

The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.

What it solves

Off Grid AI provides a complete, private AI suite that runs entirely on-device for Android, iOS, and macOS. It eliminates the need for cloud-based AI services, ensuring that no data leaves the user's device while providing a wide range of AI capabilities including text, image, and vision processing.

How it works

The application leverages native hardware acceleration (such as NPUs on Snapdragon and Core ML on iOS) and optimized libraries like llama.cpp and whisper.cpp to run models locally. It supports GGUF models for text generation and Stable Diffusion for image generation. For RAG capabilities, it uses a bundled MiniLM model for on-device embedding and SQLite for local storage of document chunks.

Who it’s for

Users who prioritize data privacy and offline access to AI tools, as well as developers who want to run LLMs, vision models, and image generators on mobile devices and Macs.

Highlights

  • Multimodal Capabilities: Supports text generation (Llama 3.2, Qwen 3, etc.), image generation (Stable Diffusion), vision AI (SmolVLM, Qwen3-VL), and voice transcription (Whisper).
  • On-Device RAG: Local knowledge base for PDFs and text documents using on-device embeddings and cosine similarity search.
  • Tool Calling: Built-in tools for web search, calculators, and knowledge base access with runaway prevention.
  • Hardware Acceleration: NPU-accelerated image generation on Snapdragon and Core ML on iOS.
  • Remote LLM Integration: Ability to connect to local network servers like Ollama or LM Studio via OpenAI-compatible APIs.
  • Pro Tier: Adds on-device text-to-speech (Kokoro), custom personas with persistent memory, and the ability to draft actions for Calendar, email, and MCP servers.