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, offline AI suite for mobile devices and Macs, ensuring that no data leaves the device. It eliminates the reliance on cloud-based AI services, providing privacy-focused text generation, image generation, and vision AI directly on local hardware.

How it works

The application leverages native hardware acceleration (Adreno GPUs via OpenCL, Apple Silicon Metal, and Snapdragon Hexagon NPUs) to run models locally. It supports GGUF models (like Llama 3.2, Qwen 3, and Phi-4) and integrates with llama.cpp and whisper.cpp for text and voice transcription. It also uses Core ML for image generation via Stable Diffusion and a local SQLite database with MiniLM for on-device RAG (Retrieval-Augmented Generation) via a project knowledge base.

Who it’s for

Users seeking total data privacy, those who need AI capabilities without an internet connection, and developers who want to run various open-source LLMs and vision models on their phones or Macs.

Highlights

  • Multimodal Capabilities: Supports text generation, image generation (Stable Diffusion), vision AI (SmolVLM, Qwen3-VL), and voice transcription (Whisper).
  • Hardware Acceleration: Optimized for Snapdragon and Apple Silicon to maximize tokens per second.
  • On-Device RAG: Local knowledge base for PDFs and text documents using on-device embeddings and cosine similarity.
  • Tool Calling: Built-in tools for web search, calculator, and knowledge base search with runaway prevention.
  • Model Management: Granular control over RAM usage with different loading policies (Lean, Balanced, Aggressive).
  • Remote LLM Support: Ability to connect to local network servers like Ollama or LM Studio.

Related

  • Project
    timmyy123/LLM-Hub

    An open-source mobile app for Android and iOS that enables 100% on-device LLM chat, image, video, and music generation for complete privacy.

  • Project
    software-mansion-labs/private-mind

    Private Mind is an on-device AI application that allows users to chat with documents, perform web searches, and process images without accounts, subscriptions, or cloud data storage.

  • Project
    google-ai-edge/gallery

    A mobile and macOS application for running open-source LLMs and multimodal AI models fully on-device, providing a private and offline experience for chat, media search, and audio transcription.

  • Project
    mudler/LocalAI

    LocalAI is an open‑source, modular server that lets you run LLMs, vision, speech‑to‑text, text‑to‑speech, image and video models on any hardware. Backends (llama.cpp, vLLM, whisper.cpp, etc.) are pulled as separate OCI images only when needed, providing OpenAI‑compatible APIs, multi‑user auth, privacy‑first on‑prem inference, and built‑in autonomous agents. It works on CPUs, NVIDIA/AMD/Intel GPUs, Apple Silicon, Vulkan and Jetson, and includes distributed scaling and a web UI/CLI.

  • Project
    katipally/openlive

    OpenLive is an open-source, local-first voice and vision layer that enables real-time, private interaction with AI models and coding agents without cloud-based audio fees.