Welcome to OllamaTor 👋

OllamaTor is a user-friendly desktop application that brings the power of Ollama's local Large Language Models (LLMs) to your fingertips. Chat with AI, adjust settings, and monitor system usage.

Features

• User-Friendly: Easy installation and intuitive interface.
• Customizable: Adjust temperature and chat history length. Many AI models.
• Resource Monitoring: Real-time CPU, RAM, and GPU (load + memory) usage monitor. + AI performance "TPM" (tokens-per-minute).
• Privacy: Your data stays local. No cloud, no tracking.
• Performance: Leverage the full power of your computer for fast responses.
• Offline Availability: Works even without an internet connection.

TO-DO:

• Stop Button to stop generating a response -> Available in v0.0.3
• fixing the math rendering (KaTeX)
• Customizable Copilots (inital prompt for the AI to get a better understanding on what it's working on)

Installation

Download Ollama.exe

Getting Started

1. Select a Model: Choose a model from the dropdown.
2. Chat: Type your prompt & click "Send".
3. Settings: Use the gear icon to change temperature and history.
4. Help: Use the help icon to start the step-by-step tour, download Ollama & get instructions to properly install models

Requirements

• Windows 10/11 (other OS not tested)
• Chrome or Edge (one of the two webbrowsers is required to run this application)
• Ollama (can also be downloaded later in OllamaTor itself; internet connection is needed)
• Downloaded Ollama models
• Python* (*OPTIONAL: for source code execution only; not needed for the compiled .exe):
  • eel
  • requests
  • psutil
  • nvidia-ml-py

Contributing

Report bugs or suggest features via GitHub Issues. Pull requests welcome!