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

# Frameworks

QBCore, Qbox, ESX and standalone. Found by itself.

Config key: `framework` in `config.json`. Default `"auto"`.

## Auto detect

With `"auto"`, core looks for these resources, in this order:

1. `qbx_core` → **Qbox** (checked first: Qbox also gives the qb-core API)
2. `qb-core` → **QBCore**
3. `es_extended` → **ESX**
4. None of them → **standalone**

Running resources win first. If none runs yet, core takes the first one that is installed and will start after it.

If the framework does not start within **30 seconds**, core stays off: `... did not start, striga-core stays disabled`.

{% hint style="warning" %}
A wrong name (for example `"framework": "qb"`) prints `config.json: unknown framework "qb", detecting automatically`. Use `qbcore`, `qbox`, `esx` or `standalone`.
{% endhint %}

## Per framework

{% tabs %}
{% tab title="QBCore" %}

```json
"framework": "qbcore"
```

* Notify goes to `QBCore:Notify` (no icon or position there).
* Text UI with `"auto"`: qb-core DrawText (or Striga Text UI when it runs).
* Inventory with `"auto"`: Striga Inventory if installed, else qb-inventory, else ox\_inventory.
* Staff groups come from `QBCore.Functions.GetPermission`.
  {% endtab %}

{% tab title="Qbox" %}

```json
"framework": "qbox"
```

* Notify goes to `exports.qbx_core:Notify`.
* Text UI with `"auto"`: ox\_lib (or Striga Text UI when it runs).
* Inventory with `"auto"`: ox\_inventory (or Striga Inventory if installed).
* Hunger, thirst and stress come from player state bags.
  {% endtab %}

{% tab title="ESX" %}

```json
"framework": "esx"
```

* Notify goes to `esx:showNotification`.
* Text UI with `"auto"`: esx\_textui when installed (or Striga Text UI when it runs), else ox\_lib.
* Inventory with `"auto"`: ox\_inventory if installed, else the ESX inventory.
* Accounts: `money` = `cash`, `bank`, `black_money` = `black`.
* Hunger and thirst come from `esx_status` (name set in `esx.statusResource`). See the ESX options in [Installation & Configuration](/docs/striga-core/installation-and-configuration.md).
  {% endtab %}

{% tab title="Standalone" %}

```json
"framework": "standalone"
```

No framework: no characters, money is 0, default job. Notifications use ox\_lib. Stress lives in the `stress` state bag and resets on reconnect.

Striga scripts still run where they can (for example Tokyo HUD shows health, armor and vehicle data).
{% endtab %}
{% endtabs %}

{% hint style="info" %}
The framework adapter is always built in. You can not replace it with `RegisterAdapter`.
{% endhint %}

{% content-ref url="/pages/yuqKlY1KGKMmWn8yt7O6" %}
[Inventory](/docs/striga-core/integration/inventory.md)
{% endcontent-ref %}


---

# 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://striga.gitbook.io/docs/striga-core/integration/frameworks.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.