A native macOS app for chatting with local LLMs served by Ollama, with multiple threads, markdown rendering and vision image support.
Jeffser/Alpaca
A GTK4/Adwaita desktop client for Ollama that lets you manage and chat with local models, with optional third-party cloud APIs.
Open-source alternative to:ChatGPT
- Stars
- 1,662
- Forks
- 149
- Open issues
- 139
- Last commit
- last month
What is it?
Alpaca is a desktop chat client built on Ollama, the local model runner. It lets you pull, delete and manage models from within the app, and chat with several models inside the same conversation. The interface is aimed at beginners who want to use local AI without working in a terminal.
Beyond local models, Alpaca can connect to cloud-hosted models that expose OpenAI-compatible APIs, using your own API keys. It supports image recognition, plain-text document input, YouTube video questions based on transcripts, and asking questions about a web page by pasting its URL. Conversations can be imported, exported, edited, and regenerated.
The app is distributed as a Flatpak through Flathub and is written in Python with GTK4 and Adwaita for a GNOME-style interface.
Key features
- 01Chat with multiple models within the same conversation
- 02Pull and delete Ollama models from the app
- 03Image and plain-text document recognition
- 04Ask questions about YouTube videos or web pages
- 05Connect to OpenAI-compatible cloud APIs with your own keys
- 06Import, export, edit and regenerate chat messages
Use cases
- Running local LLMs on a Linux desktop without using the command line
- Comparing answers from several models in one conversation
- Summarizing or asking questions about a web page or YouTube video
- Using a single chat interface for both local and cloud-hosted models
Quick start
- 1
Install Alpaca from Flathub
- 2
Read the documentation and tutorials at jeffser.com
Things to know
- Alpaca is a client, so it needs an Ollama backend to run local models.
- Licensed under GPL-3.0, a copyleft license that requires derivative works to remain open source.
In collections
Topics
FAQ
- What is Alpaca?
- A GTK4/Adwaita desktop client for Ollama that lets you manage and chat with local models, with optional third-party cloud APIs. Alpaca is a desktop chat client built on Ollama, the local model runner. It lets you pull, delete and manage models from within the app, and chat with several models inside the same conversation. The interface is aimed at beginners who want to use local AI without working in a terminal.
- Is Alpaca free to use? What license does it have?
- Alpaca is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
- Is Alpaca still maintained?
- Updated within 6 months. The last commit to Alpaca was on Oct 2, 2026.
- What can I use Alpaca for?
- Running local LLMs on a Linux desktop without using the command line Comparing answers from several models in one conversation Summarizing or asking questions about a web page or YouTube video Using a single chat interface for both local and cloud-hosted models
- How do I install Alpaca?
- Install Alpaca from Flathub Read the documentation and tutorials at jeffser.com
- Where can I get Alpaca?
- The source code and installation instructions are on GitHub: https://github.com/Jeffser/Alpaca
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A GNOME desktop app for chatting with AI models, with a focus on running models locally on Linux.
A locally deployed desktop AI chat client with MCP tool support, offering private conversation storage and connections to your own or third-party model APIs.
Cherry Studio is a cross-platform desktop AI client that connects to many LLM providers, local models and 300+ preset assistants.
A lightweight desktop AI chat client built with Tauri 2.0 and Next.js that works with cloud APIs and local models like Ollama, storing data locally.
A GTK4/libadwaita desktop app that compresses videos to a chosen target file size using local re-encoding.