LlamaGPT

Stale
GitHub TypeScript MIT

Description

LlamaGPT is a self-hosted, offline ChatGPT-like chatbot powered by Llama 2. 100% private with no data leaving your device, with Code Llama support and one-click deployment via Umbrel.

Key Features

  • 100% private and offline — no data leaves your device, fully self-hosted
  • Supports multiple Llama 2 and Code Llama models (7B, 13B, 34B, 70B)
  • One-click install on Umbrel home server via the Umbrel App Store
  • Nvidia GPU CUDA support for accelerated inference on compatible hardware
  • OpenAI-compatible API at localhost:3001 for drop-in replacement in existing apps

Use Cases

💡 Private AI chatbot for individuals who need complete data sovereignty
💡 Offline coding assistance with Code Llama models on local hardware
💡 Home lab AI deployment on Umbrel, Mac, Docker, or Kubernetes
💡 Building privacy-first AI applications using the OpenAI-compatible API

Tags

chat-ui self-hosted llama offline-ai private-ai local-llm

Categories

💬 Chat UI

Quick Start

git clone https://github.com/getumbrel/llama-gpt.git && cd llama-gpt && ./run-mac.sh --model 7b  # Access at http://localhost:3000
Visit GitHub Visit Website

Related Projects