Jeffser/Alpaca

🦙 Local and online AI hub

What it solves

Alpaca provides a beginner-friendly graphical interface for interacting with local AI models via Ollama, removing the need to use command-line tools to manage and chat with models.

How it works

It acts as a client for Ollama, allowing users to pull, delete, and chat with local models. It also supports third-party cloud-hosted AI providers (like Gemini and ChatGPT) through OpenAI-compatible APIs using personal API keys.

Who it’s for

Users who want an easy way to run and manage local AI models on their own hardware or connect to cloud-based LLMs through a unified desktop application.

Highlights

  • Multi-model conversations: Chat with multiple models within a single conversation.
  • Multimodal capabilities: Supports image recognition, plain text document recognition, and website/YouTube transcript recognition.
  • Model management: Pull and delete models directly from the app interface.
  • Chat utility: Includes code highlighting, chat import/export, and the ability to edit or regenerate messages.

Related

  • Project
    JHubi1/ollama-app

    A modern cross-platform client for Ollama that provides a graphical chat interface for interacting with local AI models via API.

  • Project
    richawo/minimal-llm-ui

    A minimalistic web interface for Ollama that allows users to chat with local LLMs, save conversation histories, and switch between models mid-chat.

  • Project
    Renset/macai

    A native macOS AI chat client that provides a unified interface for ChatGPT, Claude, Gemini, and local models via Ollama.

  • Project
    HelgeSverre/ollama-gui

    Ollama GUI is a browser‑based single‑page app that connects directly to an Ollama server, letting you chat with local LLMs. It stores chats locally (IndexedDB), supports streaming replies, versioned edits, reasoning traces, image/code attachments, model search/pull, and rich markdown rendering. You can run it via `bun` for development, build a static site, or use the provided Docker images; a live demo is hosted on Vercel. The project is MIT‑licensed and built with Vue, Vite, Tailwind, and related web tools.

  • Project
    ImDarkTom/LlamaPen

    A web-based GUI for Ollama and other local LLM providers that allows users to chat with self-hosted models via a privacy-focused interface.