> For the complete documentation index, see [llms.txt](https://agpt.co/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agpt.co/docs/platform/tutorials/download-agent-from-marketplace-local.md).

# Download & Import an Agent

## **Overview**

This guide explains how to download an agent from the AutoGPT marketplace and import it into your locally hosted instance.

## **Prerequisites**

* A local installation of AutoGPT
* Access to the marketplace for local hosters

## **Step-by-Step Process**

### **1. Access the Marketplace**

* Navigate to the marketplace section
  * Note: The interface will differ from the cloud-hosted platform

### **2. Download the Agent**

1. Browse and select your desired agent
2. Click on the agent to view details
3. Look for and click the "Download Agent" button
4. The agent file will save to your computer

### **3. Import the Agent**

1. Return to the Monitor tab
2. Locate the dropdown menu next to "Create"
3. Select "Import from File"
4. In the file selection dialog:
   * Navigate to your downloaded agent file
   * Select the file
   * Click "Open"
5. Click "Import and Edit"

### **4. Verify Import**

* The agent should now appear in your Builder
* You can begin editing or using the imported agent

## **Important Notes**

* The marketplace interface differs between local hosting and cloud-hosted versions
* Ensure you're following the local hosting specific steps
* The agent will be available in your Builder after successful import


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://agpt.co/docs/platform/tutorials/download-agent-from-marketplace-local.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.