Vibe Coding DiscoverOGAD
View on GitHubOff Grid AI — private, on-device AI. Run open models (text, vision, image, voice) locally through one OpenAI-compatible gateway. No cloud, no accounts, no API keys.
Off Grid AI is a local-first desktop runtime and studio that runs open models (text, vision, image, voice) on-device via llama.cpp, stable-diffusion.cpp, whisper.cpp and Kokoro, exposed through one OpenAI-compatible gateway. Includes chat, RAG projects, MCP connectors, artifacts, and an opt-in Pro memory layer.
Use Cases
Run open LLMs fully offline on desktopServe a local OpenAI-compatible API at 127.0.0.1:7878 for your own appsOn-device text-to-image and image-to-image generationLocal speech-to-text and text-to-speech voice modeRAG chat grounded in uploaded docs (PDF/DOCX/txt) via ProjectsUse MCP connectors inside an agentic chat loopHeadless model gateway for homelab or serverScreen-capture OCR memory, dictation, and clipboard (Pro)Private chat with vision and reasoning modelsRender model HTML/React/SVG/Mermaid artifacts in a sandbox
Built With
- Language
- TypeScript
- Frameworks
- Electron · React · TypeScript · llama.cpp · stable-diffusion.cpp · whisper.cpp · Kokoro · MCP · Vite · Vitest · Playwright · OpenAI API · Tailwind/shadcn
Tags
local-ai · on-device · privacy · offline · openai-compatible · llama.cpp · gguf · image-generation · speech-to-text · text-to-speech · mcp · rag · electron · desktop-app · vision · local-first