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

# Roo Code

> Use the Roo Code VS Code extension with NagaAI via the OpenAI-compatible API.

Roo Code can connect to NagaAI through the OpenAI-compatible API.

Use this setup if you want Roo Code to run against NagaAI models inside VS Code.

## Setup

<Steps>
  <Step title="Install Roo Code (VS Code)">
    * Open Extensions in VS Code (`Ctrl+Shift+X`)
    * Search for **Roo Code**
    * Click **Install**
  </Step>

  <Step title="Configure NagaAI as an OpenAI-compatible provider">
    In Roo Code settings, enter:

    * **Provider**: OpenAI Compatible
    * **Base URL**: `https://api.naga.ac/v1`
    * **API key**: your standard **NagaAI API key**

    <Info>
      Need an API key? Create one in the [NagaAI Dashboard](https://naga.ac/dashboard), or start with [Quickstart](/get-started/quickstart).
    </Info>
  </Step>

  <Step title="Choose a tools-capable model">
    For coding workflows, choose a model that supports function calling:

    * [Browse models with tools support](https://naga.ac/models?parameters=tools)
  </Step>

  <Step title="Verify the integration">
    Open a project in VS Code and ask Roo Code to inspect the repository or explain an implementation path. If it responds normally and can use tools when needed, the setup is working.
  </Step>
</Steps>

## Try it

* “Map the main modules in this repo and what each one does.”
* “Find where request X is handled and explain the flow.”
* “Refactor: extract this logic into a helper and update call sites.”
* “Run lint/tests and fix issues until it passes.”