Thara AI 🌿

Thara is a sharp, caring, and minimalist AI companion designed to run locally on your machine using Ollama. She thinks clearly, speaks plainly, and provides proactive advice to help you with your thoughts and tasks.

Features

• 🧠 Local Intelligence: Runs entirely on your machine via Ollama. No data leaves your system.
• 🎨 Neural Paper UI: A premium, minimalist interface with a unique "paper grain" aesthetic and smooth micro-animations.
• 🔄 Dynamic Model Selection: Fetch and switch between any locally installed Ollama models (Gemma, Llama, Mistral, etc.) directly from the UI.
• ✨ Proactive Advice: Thara doesn't just answer; she anticipates your next steps and provides helpful tips.
• 🛠️ Developer Friendly: Built-in code syntax highlighting and easy-to-use CLI.
• 📦 Pre-flight Checks: Automatically detects if Ollama is installed and offers to install it for you on Windows.

Installation

Ensure you have Node.js installed, then run:

npm install -g thara-ai

Usage

Simply run the following command in your terminal:

thara-run

The server will start at http://localhost:3000. Open it in your browser and start chatting!

Dependencies

• Ollama: You must have Ollama installed and running. If you don't have it, thara-run will offer to install it for you (Windows).
• Models: We recommend pulling gemma:2b for a fast and lightweight experience:

  ollama pull gemma:2b

Development

To run locally from source:

1. Clone the repository.
2. Install dependencies: npm install
3. Start the server: node server.js

License

ISC