> For the complete documentation index, see [llms.txt](https://docs.zenml.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zenml.io/sdk-reference/readme.md).

# Overview

ZenML and Kitaru each provide SDKs for working with their APIs:

* **ZenML** provides a Python SDK and CLI for building, managing, and deploying production-ready ML pipelines.
* **Kitaru** provides Python and TypeScript SDKs for recording, replaying, and improving AI agents. Its CLI ships with the Python package.

## ZenML SDK

The ZenML SDK provides Python tools and interfaces for building, managing, and deploying production-ready machine learning pipelines. This documentation helps you get the most out of ZenML's features.

<table data-card-size="large" data-view="cards" data-full-width="false"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>SDK Documentation</strong></td><td>Complete API documentation for all ZenML modules, classes, and functions.</td><td><a href="/files/PKM5gdbWPqO45xsxNFNg">/files/PKM5gdbWPqO45xsxNFNg</a></td><td><a href="https://sdkdocs.zenml.io">https://sdkdocs.zenml.io</a></td></tr><tr><td><strong>CLI Methods</strong></td><td>Command-line tools for managing ZenML pipelines, stacks, and deployments.</td><td><a href="/files/5GyK6exsfmXL6hySwNwh">/files/5GyK6exsfmXL6hySwNwh</a></td><td><a href="https://sdkdocs.zenml.io/latest/cli.html">https://sdkdocs.zenml.io/latest/cli.html</a></td></tr><tr><td><strong>ZenML Client</strong></td><td>Python client for interacting with ZenML projects, repositories, and services.</td><td><a href="/files/Vce5MRis737EGm6MhmR2">/files/Vce5MRis737EGm6MhmR2</a></td><td><a href="https://sdkdocs.zenml.io/latest/core_code_docs/core-client.html">https://sdkdocs.zenml.io/latest/core_code_docs/core-client.html</a></td></tr><tr><td><strong>Integrations</strong></td><td>Connect ZenML with popular ML tools, orchestrators, and cloud services.</td><td><a href="/files/K9wG5m8DIxu2isEvqWtc">/files/K9wG5m8DIxu2isEvqWtc</a></td><td><a href="https://sdkdocs.zenml.io/latest/integration_code_docs/integrations-airflow.html">https://sdkdocs.zenml.io/latest/integration_code_docs/integrations-airflow.html</a></td></tr></tbody></table>

## Kitaru SDK

[Kitaru](https://docs.zenml.io/kitaru) is ZenML's sibling project for recording, replaying, and improving AI agents: traces you can run, not just read. Its Python and TypeScript SDKs talk to the same Kitaru server over the same REST API. Framework adapters support [Python and TypeScript agents](https://docs.zenml.io/kitaru/adapters/adapters). The generated Python SDK and CLI reference is published on a dedicated site.

<table data-card-size="large" data-view="cards" data-full-width="false"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Python SDK &#x26; CLI Reference</strong></td><td>Complete generated API reference for the Kitaru Python SDK and command-line interface.</td><td><a href="https://sdkdocs.kitaru.ai">https://sdkdocs.kitaru.ai</a></td></tr><tr><td><strong>Python &#x26; TypeScript SDK Guide</strong></td><td>How both SDKs connect, authenticate, expose resources, and hand work to Kitaru workers.</td><td><a href="https://docs.zenml.io/kitaru/get-help/sdks">https://docs.zenml.io/kitaru/get-help/sdks</a></td></tr><tr><td><strong>Python Client</strong></td><td>Programmatic interface to a Kitaru server: sessions, replays, evaluators, cohorts, and experiments.</td><td><a href="/pages/Kd0a3nxMaea1jqAxQlL6">/pages/Kd0a3nxMaea1jqAxQlL6</a></td></tr></tbody></table>

<figure><img src="https://static.scarf.sh/a.png?x-pxid=f0b4f458-0a54-4fcd-aa95-d5ee424815bc" alt="ZenML Scarf"><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.zenml.io/sdk-reference/readme.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.