Skip to content

Installation

Note

oterm works with local and hosted LLM providers. For local models, point it at Ollama, vLLM, LM Studio, llama.cpp, or any OpenAI-compatible runner. For hosted providers (OpenAI, Anthropic, Groq, …), set the relevant API key. See Providers and API keys and the openaiCompatible config block.

uvx oterm
brew install oterm

Community package maintained by Rafael Dominiquini. May lag behind the latest release.

yay -S oterm

Community package maintained by Gaël James. May lag behind the latest release.

nix-env -iA nixpkgs.oterm
pip install oterm

Community package maintained by Nicola Vitale. May lag behind the latest release.

pkg install misc/py-oterm

Spoken responses

The speak capability needs the speak extra, which brings in piper-tts (GPL-3.0):

uvx "oterm[speak]"
pip install "oterm[speak]"

Updating oterm

Use the same package manager you installed with.

uvx oterm@latest
brew upgrade oterm
yay -Syu oterm
nix-env -uA nixpkgs.oterm
pip install --upgrade oterm
pkg upgrade misc/py-oterm