This project provides a modern, privacy-focused web interface for interacting with local Large Language Models (LLMs) via the Ollama API. It's designed for users who want a clean, responsive graphical front-end to manage and chat with their locally hosted AI models, offering features like Markdown support and local chat history.

How It Works

The GUI is built with Vue.js and Vite, utilizing Tailwind CSS for styling and VueUse for composition utilities. It communicates directly with a running Ollama instance, leveraging IndexedDB for local chat history persistence. This client-side focus ensures all processing and data remain local, enhancing user privacy.

Quick Start & Requirements

• Local Development: Requires Ollama and Node.js (v16+) with Yarn.
  • Install: git clone https://github.com/HelgeSverre/ollama-gui.git && cd ollama-gui && yarn install && yarn dev
  • Start Ollama: ollama pull mistral then ollama serve
• Hosted Version: Run Ollama with OLLAMA_ORIGINS=https://ollama-gui.vercel.app ollama serve.
• Docker: docker compose up -d (access at http://localhost:8080). GPU support requires uncommenting lines in compose.yml.
• Docs: https://github.com/HelgeSverre/ollama-gui

Highlighted Details

• Clean, modern interface with dark mode support.
• Local chat history persistence via IndexedDB.
• Full Markdown support in chat messages.
• Privacy-focused, with all processing handled locally.

Maintenance & Community

The project is maintained by HelgeSverre. Further community links or roadmap details beyond the listed features are not explicitly provided in the README.

Licensing & Compatibility

Released under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The project is still under active development, with features like a model library browser and mobile responsiveness planned for future releases.