> ## Documentation Index
> Fetch the complete documentation index at: https://docs.poly.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# What is the PolyAI ADK?

The **PolyAI ADK (Agent Development Kit)** is a **CLI tool and Python package** for managing **Agent Studio** projects on your local machine.

It gives you a Git-like workflow for synchronizing project configuration between your local filesystem and the Agent Studio platform.

<Note>
  **The ADK manages configuration files — it does not run your agent**

  The ADK handles pulling, editing, validating, and pushing project configuration between your local machine and Agent Studio. Agent execution — processing calls, running conversations — happens entirely inside Agent Studio. There is no local runtime.
</Note>

## What you can do with the ADK

* Build and edit Agent Studio projects locally using standard tooling
* Synchronize project configuration with Agent Studio using `poly push` and `poly pull`
* Branch, validate, and review changes before deployment
* Edit and navigate projects in **VS Code** or **Cursor** with the [PolyAI ADK extension](/adk/reference/tooling#polyai-adk-extension-for-vs-code-and-cursor), or pair the ADK with [AI coding agents](/adk/reference/tooling#claude-code) such as **Claude Code**
* Collaborate across multiple developers on the same project

## Why it exists

The ADK moves most build-and-edit work out of the browser and into your local environment. You can [merge branches](/adk/reference/branch_merge) and run reviews from the CLI, while Agent Studio remains the home for deployment and production monitoring — but you no longer have to edit resources there by hand.

Instead of editing everything directly inside Agent Studio, you pull a project locally, make changes using your normal tools, and push those changes back to the platform.

This makes it straightforward to:

* edit resources in your own editor, with the tooling you already use
* collaborate across a team without overwriting each other's work
* validate and review changes before pushing them live
* automate repetitive build work with coding tools

## Multi-developer workflows

The ADK supports team workflows out of the box. See [multi-user workflows and guardrails](/adk/concepts/multi-user-and-guardrails) for details on branching, validation, and review.

It preserves the same guardrails as Agent Studio, so developers cannot push changes that are incompatible with the project.

<Tip>
  **Git-like, but for Agent Studio**

  Think of the ADK as the local development layer for Agent Studio: pull, edit locally, validate, and push.
</Tip>

## Next steps

<CardGroup>
  <Card title="Watch the walkthrough" href="/adk/get-started/walkthrough-video">
    See a practical demonstration of the ADK in use.
  </Card>

  <Card title="Install prerequisites" href="/adk/get-started/prerequisites">
    Set up uv, Git, and your API key before running your first commands.
  </Card>

  <Card title="Run your first commands" href="/adk/get-started/first-commands">
    Initialize a project, pull configuration, and push your first change.
  </Card>
</CardGroup>