JAZ Documentation
JAZ is a Python framework for building and optimizing LLM agents through a code-first REPL loop. The LLM generates code, runs it, observes the results, and iterates until the task is complete — so your agent workflows are predictable, auditable, and cost-aware.
from jaz import invokefrom jaz.hooks import ReturnType
result = invoke(ReturnType(int), task="Calculate the factorial of 10")print(result) # 3628800Start here
Section titled “Start here”InstallationInstall JAZ and set up your API keys.
Quick startRun your first agent in a few lines.
ConceptsThe core vocabulary — invoke, the REPL loop, hooks, and budgets.
TutorialsHands-on Colab notebooks — no install required.
API referenceThe public jaz API surface.
Why JAZ
Section titled “Why JAZ”- Code beats prose for workflows. Reasoning expressed as code is more predictable and auditable than natural-language-only agents.
- Recursive composition. Agents invoke nested agents, each with its own budget.
- Built-in observability. Logging and OpenTelemetry tracing via composable hooks.
- Cost control. Enforce cost and call-count budgets across the whole recursion tree.
Prefer to learn by doing? Jump straight into a Colab tutorial.
Community
Section titled “Community”Questions, ideas, or something that didn’t work? Join the JAZ Discord to ask the people building it, or open an issue on GitHub.