Ross ROSS = Recommend OSS · open-source software intelligence for agents

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. observed · 2026-08-28

github.com/off-grid-ai/OGAM · homepage · TypeScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

78/100

  • Activity 99
  • Release rhythm 86
  • Longevity 15
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0.0
  • age_days: 216
  • days_rel: 12
  • days_push: 7
  • n_releases_24m: 91

Full methodology

Adoption not part of the score

3002 stars · 290 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Off Grid AI (OGAM) is a cross-platform mobile and desktop application that runs AI entirely on-device: GGUF LLM chat with vision, Whisper speech-to-text, Kokoro text-to-speech, Stable Diffusion image generation, tool calling, and MCP server connections. It requires no account or API key and no data leaves the device, with an optional paid Pro tier adding voice mode, personas, and device sync.

Use cases

  • chat with an LLM offline on my phone
  • run speech-to-text on device with whisper
  • generate images locally with stable diffusion on android
  • private AI assistant with no data leaving my device
  • run GGUF models on iPhone or Mac
  • connect a local AI assistant to MCP servers like Notion or GitHub
  • use AI with no internet connection or API key
  • on-device vision language model to analyze images

When to choose

  • you need AI chat, vision, speech, or image generation fully offline for privacy
  • you want a no-account, no-API-key local AI app on Android, iOS, or macOS
  • you want tool calling and MCP integrations that stay on your hardware
  • you work in air-gapped or low-connectivity environments

When to avoid

  • you need the largest frontier models that cannot fit on consumer devices
  • you want a server-side or cloud-hosted inference deployment
  • you need Linux desktop support or a headless API service
  • you require team collaboration or shared cloud storage of conversations

Facets

application · maturity active

llm-inference speech-recognition tts stable-diffusion chatbot agent-framework mcp image-processing artificial-intelligence large-language-models privacy mobile-development self-hosted windows cross-platform offline-ai on-device gguf llama-cpp whisper-cpp react-native local-models privacy-first voice-mode tool-calling android ios macos

8 sources

Member repositories

RepositoryRoleHealth v2
off-grid-ai/OGAMmain78

For agents

markdown · JSON · MCP: product_card(name="off-grid-ai/OGAM")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem