Welcome to ZenML

Build production ML pipelines with ZenML and improve agentic systems with Kitaru.

ZenML is an open-source framework for orchestrating production ML and LLM pipelines, including pipelines that run agentic workloads.

That story has two open-source projects behind it:

• ZenML is the MLOps framework: portable, production-ready pipelines for ML and LLM workloads, with versioned artifacts, caching, and infrastructure abstracted behind stacks.
• Kitaru is for evaluating and improving agentic systems. It turns recorded or imported production traces into sessions for investigation, cohorts, evaluators, replay experiments, regression testing, and CI.

Each works on its own. ZenML orchestrates pipelines; Kitaru provides evals and improvement loops for agentic systems. Kitaru runs its own lightweight server, with workers that execute replays in your environment.

What are you building?

Pick the path that matches your work. Neither path requires the other, and adopting the second one later doesn't mean starting over.

ML Pipelines → ZenML

Build, version, and deploy classical ML and LLM pipelines. Start with Hello World, then the Starter guide.

Agent evals → Kitaru

Investigate production traces, define evaluators and cohorts, and test changes through replay experiments. Start with the Kitaru quickstart.

How these docs are organized

The documentation is split into spaces — the tabs at the top of this page. Knowing what lives where saves you a lot of searching:

Space	What you'll find there
ZenML (you are here)	The pipelines framework: installation, core concepts, deployment, and how-to guides
Kitaru	Agent evals and improvement loops: production sessions, investigations, cohorts, evaluators, replay experiments, and regression testing
Learn	Narrative ZenML guides: Starter, Production, and LLMOps, plus tutorials and best practices
Stacks	The infrastructure components — orchestrators, artifact stores, and more — that ZenML pipelines run on
SDK reference / API reference	Client and REST API references, organized per project
Changelog	Release notes, version by version

First steps

Whichever path you picked, the first steps are the same shape: install, run something real, then learn the concepts.

	ML Pipelines (ZenML)	Agent Evals (Kitaru)
Install	Installation	Installation
First run	Hello World	Quickstart
Concepts	Core Concepts	Core Concepts

If you use AI coding tools, see LLM tooling for ZenML's MCP server and Agent Skills (including zenml-scoping and zenml-pipeline-authoring).

Guides

Starter Guide

Get started with ZenML fundamentals and set up your first pipeline

Production Guide

Move your ML pipelines from development to production

Kitaru

Replay a real run with one change, and improve agents across a cohort of real runs