> For the complete documentation index, see [llms.txt](https://docs.arcee.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.arcee.ai/integration-list/kilo-code.md).

# Kilo Code

Kilo Code is an open-source AI coding agent that integrates directly into VS Code to support code generation, refactoring, terminal automation, and browser-based workflows using large language models (LLMs).

Kilo Code supports custom OpenAI-compatible providers, allowing you to connect directly to the **Arcee AI API** and access **open models** without a third-party proxy. This provides a direct connection to Arcee's inference platform with full access to all available models.

This guide walks through how to configure Kilo Code to use open models via the Arcee AI API.

***

**Prerequisites**

* Arcee AI Account
  * If you don't have an account, sign up at [platform.arcee.ai](https://platform.arcee.ai).
* Arcee AI API Key

**Quickstart**

1. Install Kilo Code
   1. Open the Extensions panel in VS Code and search for **Kilo Code**, then click **Install**.
2. Open Kilo Code Settings
   1. Click the Kilo Code icon in the left sidebar to open the panel, then click the gear icon (⚙️) in the top right corner.
3. Add Arcee AI as a Custom Provider
   1. Navigate to the **Providers** tab.
   2. Scroll down to **Custom provider** and click **+ Connect**.
   3. Enter the following settings:
      * **Provider ID:** `arcee-ai`
      * **Display Name:** `Arcee AI`
      * **Base URL:** `https://api.arcee.ai/api/v1`
      * **API Key:** Your Arcee AI API key
4. Add Models
   1. Kilo Code should automatically detect and add available models. If it does not, manually add the **Model ID** ([here](/get-started/pricing.md)), and and intuitive **Display Name**.
5. Set Default Model *(Optional)*
   1. Navigate to the **Models** tab.
   2. Under **Default Model**, select **Arcee AI / \<Display Name>** from the dropdown.

Once configured, Kilo Code will route all requests directly through the Arcee AI API using the selected model.