> For the complete documentation index, see [llms.txt](https://docs.flashback.tech/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flashback.tech/guides/setup-the-cloud-and-ai-gateway/start-with-cloud-storage-1/create-a-repository.md).

# Create a Repository

{% hint style="info" %}
Before creating repositories, read [Repositories](/flashgate-platform/cloud-and-ai-gateway/repositories.md), [Configure a Bucket](/guides/setup-the-cloud-and-ai-gateway/start-with-cloud-storage/create-a-bucket.md), and [Configure an AI LLM](/guides/setup-the-cloud-and-ai-gateway/start-with-cloud-storage/create-a-bucket-1.md).
{% endhint %}

{% hint style="danger" %}
UI labels can evolve over time. If a button/label slightly differs in your workspace, follow the same flow and contact us on [Discord](https://discord.com/invite/yy8kyM5qFB) if needed.
{% endhint %}

## What changed in the UI

The **Repositories** area is now a top-level section in **Cloud and AI Gateway** (not only a storage sub-section). It is organized into three categories:

* **Overview**: global view of repository activity and quick access to repository details.
* **Inventory**: list of all repositories; this is where you usually create repositories.
* **API Keys**: centralized list of repository API keys across repositories.

You can create a repository from **Overview** or **Inventory** using the **Add** button.

## Repository properties to define at creation time

When you create a repository, focus on these properties:

1. **Name**
   * Human-readable identifier (for example `prod-eu-data`, `assistant-ai-gateway`).
2. **API endpoint type**
   * Select the protocol your applications will use for this repository:
     * **S3**, **GCS**, or **Azure Blob** for storage resources.
     * **OpenAI** for AI LLM resources.
3. **Initial resources**
   * You can attach existing resources during creation, then add more later.
   * Supported resource families include:
     * Cloud Storage buckets/containers/accounts
     * AI LLM configurations
     * Packets (if enabled in your workspace UI)

{% hint style="danger" %}
To avoid collisions and keep the repository virtual namespace coherent, apply these rules during creation:

* **S3 & GCS storage resources**
  * Bucket names must be unique **across providers** inside the same repository.
  * You **cannot** mix an S3 bucket named `mybucket` with a GCS bucket also named `mybucket` in one repository.
* **Azure Blob storage resources**
  * Azure storage **account names** must not collide with S3/GCS bucket names in the same repository.
  * You **cannot** combine:
    * an S3 or GCS bucket called `mystorage`
    * with an Azure container under a storage account also called `mystorage` in the same repository.
  * You **may** include multiple containers from the same Azure storage account in one repository.
    {% endhint %}

{% hint style="warning" %}
Do **not** generate API keys during repository creation. API key generation belongs to repository configuration and is covered in [Configure a Repository](/guides/setup-the-cloud-and-ai-gateway/start-with-cloud-storage-1/program-with-flashgate.md).
{% endhint %}

## Instructions

{% stepper %}
{% step %}

### Open Repositories

Open **Cloud and AI Gateway** and go to **Repositories**.
{% endstep %}

{% step %}

### Choose where to create

Open either:

* **Overview** and click **Add or (+) button**, or
* **Inventory** and click (**+)** .
  {% endstep %}

{% step %}

### Fill repository basics

Complete the form:

* **Name**
* Optional description/labels (if available in your UI)
  {% endstep %}

{% step %}

### Attach initial resources

Use **Add resource** to attach one or more existing resources (Storage, AI LLM) with **API endpoint type** (**S3**, **GCS**, **Azure Blob**, or **OpenAI** depending on your use case).

For storage resources, keep a collision-free namespace inside the same repository:

* You cannot attach two resources that create naming conflicts in the exposed virtual namespace.
* Typical collision case: same bucket/account identifier reused across providers in one repository.

{% hint style="danger" %}
Collision reminder:

* S3 and GCS names must stay unique across providers inside the same repository.
* Azure storage account names must not overlap with S3/GCS identifiers in that repository.
  {% endhint %}
  {% endstep %}

{% step %}

### Save the repository

Click **Finish Setup**. The repository appears in **Inventory** and is visible in **Overview** (depending on the usage).
{% endstep %}
{% endstepper %}

### Continue with configuration

Open your new repository and continue with [Configure a Repository](/guides/setup-the-cloud-and-ai-gateway/start-with-cloud-storage-1/program-with-flashgate.md) to:

* add/remove resources,
* review endpoint and SDK details,
* generate and manage API keys.

## Related API references

If you automate repository creation/configuration:

* [Repository Management APIs](/support-reference/platform-api-reference/repo-management.md)
* [Bucket Management APIs](/support-reference/platform-api-reference/storage-apis/bucket-management.md)
* [AI LLM Management APIs](/support-reference/platform-api-reference/ai-apis/ai-llms.md)


---

# 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.flashback.tech/guides/setup-the-cloud-and-ai-gateway/start-with-cloud-storage-1/create-a-repository.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.