mdllama 4.2.0

A command-line interface for Ollama API

mdllama

A CLI tool that lets you chat with Ollama and OpenAI models right from your terminal, with built-in Markdown rendering.

mdllama makes it easy to interact with AI models directly from your command line, meanwhile providing you with real-time Markdown rendering.

Features

• Chat with Ollama models from the terminal
• Built-in Markdown rendering
• Simple installation and removal (see below)

Screenshots

Chat Interface

Help

Live Demo

Go to this mdllama demo to try it out live in your browser. The API key is 9c334d5a0863984b641b1375a850fb5d

[!NOTE] Try asking the model to give you some markdown-formatted text, like:

Give me a markdown-formatted text about the history of AI.

So try it out and see how it works!

Installation

Install using package manager (recommended)

Debian/Ubuntu Installation

1. Add the PPA to your sources list:

   echo 'deb [trusted=yes] https://packages.qincai.xyz/debian stable main' | sudo tee /etc/apt/sources.list.d/qincai-ppa.list
   sudo apt update
   

2. Install mdllama:

   sudo apt install python3-mdllama
   

Fedora Installation

1. Download the latest RPM from: https://packages.qincai.xyz/fedora/

   Or, to install directly:

   sudo dnf install https://packages.qincai.xyz/fedora/mdllama-<version>.noarch.rpm
   

   Replace <version> with the latest version number.

2. (Optional, highly recommended) To enable as a repository for updates, create /etc/yum.repos.d/qincai-ppa.repo:

   [qincai-ppa]
   name=Raymont's Personal RPMs
   baseurl=https://packages.qincai.xyz/fedora/
   enabled=1
   metadata_expire=0
   gpgcheck=0
   

   Then install with:

   sudo dnf install mdllama
   

3, Install the ollama library from pip:

pip install ollama

You can also install it globally with:

sudo pip install ollama

[!NOTE] The ollama library is not installed by default in the RPM package since there is no system ollama package avaliable (python3-ollama). You need to install it manually using pip in order to use mdllama with Ollama models.

---

Traditional Bash Script Installation (Linux)

To install mdllama using the traditional bash script, run:

bash <(curl -fsSL https://raw.githubusercontent.com/QinCai-rui/mdllama/refs/heads/main/install.sh)

To uninstall mdllama, run:

bash <(curl -fsSL https://raw.githubusercontent.com/QinCai-rui/mdllama/refs/heads/main/uninstall.sh)

---

Windows & macOS Installation

Install via pip (recommended for Windows/macOS):

pip install mdllama

License

This project is licensed under the GNU General Public License v3.0. See the LICENSE file for details.

---