< cd ../gallery

[AI & ML]

PAI by nirholas

go to website ↗github

A complete private computer on a USB stick. PAI is a bootable Debian 12 Linux distro that runs Ollama locally on any x86_64 or ARM64 machine — full desktop, local AI, hardened networking, all in RAM. Plug in, boot in seconds, work anywhere, pull the stick and nothing stays behind. Your AI on your hardware, no cloud, no accounts. https://pai.direct. Maintained by nirholas on GitHub, where it has earned 103 stars from the community.

maintainer

★ 103 stars

12 forks

# install

# tags

Shell Ai Claude Crypto Cryptocurrency

languages

last commit2mo ago

license—

latest versions

more Ollama repos

Deploy a complete self-hosted AI stack with Docker Compose: Ollama, LiteLLM, AnythingLLM, Whisper, WhisperLive, Kokoro, Embeddings, Docling and MCP Gateway. Local-first, private by default, with lightweight stacks, optional HTTPS and NVIDIA CUDA acceleration. Multi-arch: amd64, arm64. Maintained by hwdsl2 on GitHub, where it has earned 132 stars from the community.

A collection of zipped Ollama models for offline use. Simply download, extract, and set up your desired model anywhere. Maintained by Pyenb on GitHub, where it has earned 94 stars from the community.

A one-file Ollama CLI client written in bash. Maintained by Biont on GitHub, where it has earned 32 stars from the community.