Getting Started


It is recommended you install this package in a virtualenv.

# Python 3.10 or higher is required
python3 -m venv .venv
source .venv/bin/activate

Install the package from PyPI:

python -m pip install mentat

From github:

python -m pip install git+

Or via brew:

brew install mentat


If you want to use the whisper transcription on an OS besides macOS or Windows you will need to install PortAudio. For instance, on Ubuntu:

sudo apt-get install libportaudio2

Basic Usage

Start mentat with a list of files you want mentat to be able to read and edit and ask for what you want:

mentat file1 file2 file3

You can add and remove files from context in a session with the /include and /exclude commands. For more on context see Context. For a list of all commands see Commands or enter /help in a mentat session.