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

# DeepSeek Harness

[DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) is an open-source Agent Harness from DeepSeek, built around an "everything is a plugin" design. It provides a Web UI and can connect to OpenAI-compatible endpoints through custom providers, so you can use ScitiX models in DeepSeek Harness agent tasks.

This guide covers the npm run method. DeepSeek Harness also supports running from source; see the official documentation for details.

## Configure

### 1. Install Node.js

DeepSeek Harness requires Node.js. Open a terminal and run:

```bash theme={null}
node -v
```

If the command returns a version number, Node.js is installed. If not, download and install it from the [Node.js website](https://nodejs.org/en/download).

### 2. Start DeepSeek Harness

Run:

```bash theme={null}
npx @deepseek-ai/dsh web
```

The first run downloads the required dependencies and may take some time. After startup, DeepSeek Harness opens the local Web UI by default:

```text theme={null}
http://127.0.0.1:3080/
```

<Warning>
  DeepSeek Harness is in developer preview, and version upgrades may introduce breaking changes. It can execute model-generated code and commands. Before running an agent, check the selected workspace, permissions, and requested actions.
</Warning>

### 3. Add ScitiX as a provider

Create an API Key on the [API Keys](https://console.scitix.ai/model-inference/api_keys) page first.

In the DeepSeek Harness Web UI, open **Settings > Models**, then choose **Add a custom provider**.

Fill in the following fields, then create the provider.

<img src="https://mintcdn.com/scitix-adfc65c2/9QQCAulo6uf0f0dB/model-inference/media/deepseek-harness-provider-config-en.png?fit=max&auto=format&n=9QQCAulo6uf0f0dB&q=85&s=c38a5ff56ffb08f1af0aaf5b0bff2ff6" alt="DeepSeek Harness custom provider configured with ScitiX" width="2886" height="1348" data-path="model-inference/media/deepseek-harness-provider-config-en.png" />

| Field        | Value                                                                                                                                                                                                                                                                                         |
| ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Provider ID  | A custom provider ID, such as `scitix`. Use lowercase letters.                                                                                                                                                                                                                                |
| Display name | A custom display name, such as `scitix`.                                                                                                                                                                                                                                                      |
| Base URL     | `https://api.scitix.ai/model-api/v1`                                                                                                                                                                                                                                                          |
| API protocol | `openai-completions`                                                                                                                                                                                                                                                                          |
| API Key      | Your API Key created on the [API Keys](https://console.scitix.ai/model-inference/api_keys) page. Keep it secure. Do not commit it to Git or include it in public issues, logs, or screenshots.                                                                                                |
| Models       | Click **Fetch available models** to fetch the model list, or add model IDs manually. For available models and pricing, see [Models](https://console.scitix.ai/model-inference/models). For agent tasks that rely on tool calls, choose a model that supports Function Calling / tool calling. |

### 4. Select runtime settings

Return to the DeepSeek Harness main screen and check the following settings before starting a task:

* **Workspace**: select the workspace the agent can access. DeepSeek Harness reads files, runs commands, and executes tasks within the selected workspace.
* **Model**: select the ScitiX model you added from the model picker.
* **Mode**: choose a runtime mode based on the task. DeepSeek Harness provides **Standard mode**, **PTC mode**, **Minimal mode**, and **Creator mode**. For first-time verification, you can keep the default Standard mode.

<img src="https://mintcdn.com/scitix-adfc65c2/9QQCAulo6uf0f0dB/model-inference/media/deepseek-harness-runtime-settings-en.png?fit=max&auto=format&n=9QQCAulo6uf0f0dB&q=85&s=a4670665681449f072088c26003405bc" alt="DeepSeek Harness runtime settings with workspace, mode, and model selected" width="2844" height="1362" data-path="model-inference/media/deepseek-harness-runtime-settings-en.png" />

## Verify

With a ScitiX model selected, send a simple task:

```text theme={null}
List three common uses of generative AI in software development.
```

A normal response means the configuration is successful.