Local LLaMA – Ollama GUI is a sleek, locally hosted web interface designed for interacting with AI models served by Ollama. Built with a local-first approach, it connects to your Ollama instance (default: http://localhost:11434), discovers available models, and lets you chat with them seamlessly.

Key Features:

- Streaming Responses: Real-time, token-by-token output for smooth conversations.

- Model Discovery: Auto-detects and allows quick switching between Ollama models.

- Persistent Chat History: Stores conversations locally in your browser using IndexedDB.

- Markdown Support: Renders formatted text, code blocks, and lists cleanly.

- Themes & UX: Light/dark mode toggle and keyboard-friendly controls (e.g., Enter to send).

Tech Stack:

Next.js 15, React 19, Tailwind CSS, and Dexie for offline storage. Requires Node.js ≥18.18 and a local Ollama server with at least one model (e.g., `llama3`).

Ideal for developers and enthusiasts seeking a privacy-focused, lightweight GUI to explore Ollama models without cloud dependencies.