Overview

Guides, examples and projects

Discover how to build production-ready ML pipelines and production-grade AI agents with ZenML and Kitaru through our curated learning resources. Whether you're looking for step-by-step instructions, complete project implementations, or specific examples, you'll find resources to accelerate your workflow.

Kitaru is ZenML's sibling project for production AI agents: run, replay, improve. Every model call and tool call in a run is recorded as a durable checkpoint, so you can replay a real run with one thing changed (a different model or prompt), diff the two, then roll the winning change across a cohort of recent runs. A Kitaru flow is a dynamic ZenML pipeline under the hood, so agents and pipelines share the same stacks, server, and dashboard. It has its own learning track below.

Guides

Step-by-step instructions to help you master ZenML concepts and features.

Starter Guide

Get started with ZenML fundamentals and set up your first pipeline

Production Guide

Move your ML pipelines from development to production

LLMOps Guide

Build and deploy Large Language Model pipelines

Agents Guide

Run, replay, and improve AI agents with Kitaru: record runs as durable checkpoints, replay a real run with one change and diff it, then scale the winning change across a cohort.

Tutorials

Deep dives into advanced topics

Projects

Complete end-to-end implementations that showcase ZenML in real-world scenarios. See all projects in our website →

FloraCast

A production-ready MLOps pipeline for time series forecasting using ZenML and Darts, featuring TFT-based training and scheduled batch inference.

LLM-Complete Guide

Production-ready RAG pipelines from basic retrieval to advanced LLMOps with embeddings finetuning and evals.

Retail Forecast

A robust MLOps pipeline for retail sales forecasting designed for retail data scientists and ML engineers.

Research Radar

Automates research paper discovery and classification for specialized research domains.

OncoClear

A production-ready MLOps pipeline for accurate breast cancer classification using machine learning.

Sign Language Detection with YOLOv5

End-to-end computer vision pipeline

ZenML Support Agent

A production-ready agent that can help you with your ZenML questions.

OmniReader

A scalable multi-model OCR workflow framework for batch document processing and model evaluation.

EuroRate Predictor

Turn European Central Bank data into actionable interest rate forecasts with this comprehensive MLOps solution.

Examples

Focused code snippets and templates that address specific ML workflow challenges. See all examples in GitHub →

Quickstart

Bridging Local Development and Cloud Deployment

End-to-End Batch Inference

Supervised ML project built with the ZenML framework and its integration.

Agent Architecture Comparison

Compare AI agents with LangGraph workflows, LiteLLM integration, and automatic visualizations.

Agent Framework Integrations

Production-ready integrations for 11 popular agent frameworks including LangChain, CrewAI, AutoGen, and more.

Deploying Agents

Document analysis service with pipelines, evaluation, and embedded web UI.

Agent Outer Loop

Agent training and evaluation loop: evolve a generic agent into a specialized support system through intent classification and model training.

Basic NLP with BERT

Build NLP models with production-ready ML pipeline framework

Computer Vision with YoloV8

End-to-end computer vision pipeline with modular design

LLM Finetuning

LLM fine-tuning pipeline with PEFT approach

Durable Agent Platform (Kitaru)

The runnable code behind the Agents guide: an internal agent harness platform with Kitaru and PydanticAI.

NextStarter guide

Last updated 18 days ago

Was this helpful?