portable-ai

A 100% offline, fully portable, zero-trace AI (Ollama + Llama 3 + AnythingLLM) that runs natively from a USB drive on Windows and Mac.

The ultimate zero-install, portable local AI environment. Run high-quality, uncensored LLMs (Gemma, Qwen, NemoMix) directly from any USB drive or SSD. Fully air-gapped, cross-platform (Win/Mac/Linux), and privacy-first with persistent chat history.

Portable offline AI kit on a USB SSD — run LLM chat + Wikipedia + encrypted vault anywhere. No internet, no install, no subscriptions. Windows/macOS/Linux/Android/iOS. Powered by Qwen3 + llamafile.

Local AI is a fully offline, portable workspace where users can download, manage, and chat with powerful Ollama models privately, featuring smart context memory.

Portable desktop AI agent in a single .exe. LangGraph + MCP: files, shell, web search, processes. Safe by design — human-in-the-loop approvals for critical actions. Self-correcting, auto-retry, API-key rotation. Multimodal & multi-model (OpenAI-compatible, Anthropic, Gemini). No Docker, no installers — copy and run.

🔌 Portable uncensored AI agent that runs from USB/SSD. 13 autonomous tools (deep search, OSINT, code execution), persistent memory, 5 GGUF models, zero install, zero traces. Cross-platform (Windows + Linux).

Run any GGUF language model locally including Uncensored AI models. Runs on Linux, macOS, and Windows. One script to set up everything.

🦾 Portable Jarvis-like AI assistant that runs entirely from a USB drive - 100% offline, voice commands, computer control

ESP32 S3 and AI powered edge cloud hybrid voice assistant with custom hardware and real time audio pipeline.

A fully offline, portable private AI assistant that runs Qwen3 locally without cloud APIs or internet access.

Portable, privacy-first offline AI workstation proof of concept using llama.cpp, GGUF models, local browser inference, resource-aware model routing, PowerShell automation, local RAG architecture, and real hardware validation from a removable drive.

Portable Offline AI Assistant with Local LLM, PDF RAG, Whisper STT and Piper TTS

Deploy a validated vLLM container for Gemma 4 31B Deckard Heretic using NVFP4 quantization and z-lab DFlash speculative drafting.

AI Avatar Protocal (AIAP) -An open standard for user-owned, verifiable, portable and extensible personal AI Avatars.

Portable local inference and offline AI workspace

可跨 Agent、模型和电脑携带的本地优先 AI 助手成长层，让记忆、能力、经验与 SOP 持续积累。

基于官方 Kilo 构建便携版项目 · 运行时内置，开箱即用，全平台覆盖

Reference OpenClaw adapter for AI Avatar Protocol (AIAP), enabling protable AI Avatar identity, ownership and interoperability.