A straightforward web-based chat application that connects you with multiple AI models including Gemini 2.0, Gemini 1.5 variants, and NVIDIA Llama Nemotron models. Customize your chat experience with this open-source solution.
Explore the simple and clean interface of our AI chat application across desktop and mobile devices.
Connect with multiple AI models including Gemini 2.0 Flash, Gemini 1.5 variants, and NVIDIA Llama Nemotron models through a simple web interface with PostgreSQL database for conversation history.
Personalize your chat experience with theme options, adjustable font sizes, and model parameter controls like temperature settings.
Access your AI chat through any web browser. Built with Node.js and Express, easy to deploy on various platforms.
Built as an open-source project with secure API key management. Your API keys are stored locally and used only for your requests.
Choose from multiple AI models based on your requirements:
Model | Provider | Best For | Version |
---|---|---|---|
Gemini 2.0 Flash | Latest model, fast responses | 2.0 | |
Gemini 2.0 Flash Lite | Lightweight version, quick tasks | 2.0 | |
Gemini 1.5 Flash | Balanced performance and speed | 1.5 | |
Gemini 1.5 Flash 8B | 8B parameter model, efficient | 1.5 | |
Gemini 1.5 Pro | Complex tasks, detailed responses | 1.5 | |
Llama-3.1-Nemotron-Nano-8B-v1 | NVIDIA | Compact open-source model | 3.1 |
Llama-3.3-Nemotron-Super-49B-v1 | NVIDIA | Large parameter open-source model | 3.3 |
Lead Developer
Developer