Installation
JAZ is an open-source Python framework for building LLM (AI) agents that write and run their own code: you describe a task, the agent writes Python, runs it, and returns a typed result. (See Concepts for the full mental model.)
Prerequisites
Section titled “Prerequisites”- Python ≥ 3.12
Install
Section titled “Install”JAZ is published to PyPI as jaz-lang (the import name
is jaz):
pip install jaz-langOptional extras (for example, distributed tracing):
pip install "jaz-lang[tracing]"import jaz # the package installs as jaz-lang but imports as jazAPI keys
Section titled “API keys”JAZ talks to model providers through LiteLLM by default, so it
reads the standard provider environment variables. A model is named by a LiteLLM route like
openai/gpt-5-mini or anthropic/claude-sonnet-4-5, and the provider prefix decides which
key is needed.
The Quick start and guide examples use an OpenAI model (openai/gpt-5-mini), so set
OPENAI_API_KEY to follow along. To use a different provider, configure the model and
set that provider’s key instead (see Budgets & configuration).
Provide the key via either:
- Shell profile — add
export OPENAI_API_KEY=sk-...to~/.zshrcor~/.bashrc(simplest, available globally). .envfile — create a.envat your project root with oneKEY=valueper line, then load it with direnv (dotenvin an.envrc) or your editor’s env support.
export OPENAI_API_KEY=sk-...export ANTHROPIC_API_KEY=sk-ant-...Next step
Section titled “Next step”Continue to the Quick start to run your first agent — or skip the install entirely and try a Colab notebook.
Stuck on the install? Ask in the JAZ Discord.