Linux
Quick install instructions
Dependencies
Supported Versions
As of Talemate 0.30 the following python versions are supported: 3.10, 3.11, 3.12 or 3.13
install.sh downloads a portable Node.js 22 runtime automatically (used to build the frontend), so you do not need to install Node.js yourself.
Installation
git clone https://github.com/vegu-ai/talemate.gitcd talematesource install.sh- When asked if you want to install pytorch with CUDA support choose
yif you have a CUDA compatible Nvidia GPU and have installed the necessary drivers.
- When asked if you want to install pytorch with CUDA support choose
source start.sh
If everything went well, you can proceed to connect a client.
Additional Information
Setting Up a Virtual Environment
- Open a terminal.
- Navigate to the project directory.
- uv will automatically create a virtual environment when you run
uv venv.
Installing Dependencies
- Use uv to install dependencies by running
uv pip install -e ".[dev]".
Running the Backend
- You can start the backend server using
uv run src/talemate/server/run.py runserver --host 0.0.0.0 --port 5050.
Running the Frontend
Unlike the quick install above, this manual path does not provision Node.js for you — install Node.js 22+ yourself (see here). Corepack ships with it and provides pnpm.
- Navigate to the
talemate_frontenddirectory. - If you haven't already, install frontend dependencies by running
corepack pnpm install. - Start the server with
corepack pnpm run serve.
Please note that you may need to set environment variables or modify the host and port as per your setup. You can refer to the various start scripts for more details.