> ## Documentation Index
> Fetch the complete documentation index at: https://docs.a2agent.me/llms.txt
> Use this file to discover all available pages before exploring further.

# Use DeepSeek Harness with A2Agent

> Run DeepSeek Harness locally and connect it to A2Agent through the Web UI. Use DeepSeek, Kimi, GLM, MiniMax, Qwen, and other supported models through a single A2Agent API key.

DeepSeek Harness is an open-source agent harness with a local Web UI. After starting the local server, you can configure A2Agent from **Settings → Models**, choose a model, select a workspace, and run tasks directly in your browser.

## Prerequisites

* An A2Agent API key — [sign up at a2agent.me/register](https://a2agent.me/register) to get one
* A model ID listed on the [A2Agent Models page](https://a2agent.me/models)

DeepSeek Harness is currently in the Developer Preview stage. Future releases may include breaking changes.

## Setup

<Steps>
  <Step title="Start the local Web UI">
    Run the following command:

    ```bash theme={null}
    npx @deepseek-ai/dsh web --no-open
    ```

    The `--no-open` option prevents DeepSeek Harness from trying to open a browser automatically.

    When the server starts, it normally listens at:

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

    Keep the terminal running while you use the Web UI.
  </Step>

  <Step title="Open DeepSeek Harness in your browser">
    Open:

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

    If `localhost` is not available, try:

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

  <Step title="Open the model settings">
    In the DeepSeek Harness Web UI, go to:

    ```text theme={null}
    Settings → Models
    ```

    Choose:

    ```text theme={null}
    Add custom provider
    ```

    This option is used to connect an OpenAI-compatible gateway or another provider that is not included in the built-in catalog.
  </Step>

  <Step title="Configure the A2Agent provider">
    Enter the following values:

    | Field | Value |
    | :- | :- |
    | Provider ID | `a2agent` |
    | Display name | `A2Agent` |
    | Base URL | `https://api.a2agent.me/v1` |
    | API protocol | `OpenAI Completions` |
    | API key | Your A2Agent API key |

    Use this Base URL exactly:[https://api.a2agent.me/v1](https://api.a2agent.me/v1)
  </Step>

  <Step title="Add A2Agent models">
    Under **Model catalog**, choose:Fetch available models

    DeepSeek Harness will query the OpenAI-compatible models endpoint and display the models available through A2Agent.

    Select the models you want to use, then save the provider.

    If model discovery does not work, add model IDs manually. Use the exact IDs shown on the [A2Agent Models page](https://a2agent.me/models).
  </Step>

  <Step title="Return to the homepage and select a model">
    After saving the A2Agent provider, return to the DeepSeek Harness homepage.Open the model selector and select one of the available models.

    The selected model becomes the model used for new sessions.
  </Step>
</Steps>

## Stop and restart the Web UI

To stop the local server, return to the terminal running DeepSeek Harness and press:

```text theme={null}
Ctrl+C
```

To start it again, run:

```bash theme={null}
npx @deepseek-ai/dsh web --no-open
```

Then open:

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

## Troubleshooting

<AccordionGroup>
  <Accordion title="401 Unauthorized">
    DeepSeek Harness reached A2Agent, but the API key was rejected.

    * Confirm that the key is a valid A2Agent API key.
    * Make sure the complete key was entered.
    * Check for accidental spaces or line breaks.
    * Do not use an API key from another provider.
    * Reopen **Settings → Models** and update the saved credential.
  </Accordion>
</AccordionGroup>

<Accordion title="Endpoint verification failed">
  Confirm that the Base URL is exactly:[https://api.a2agent.me/v1](https://api.a2agent.me/v1)

  A2Agent uses the OpenAI-compatible protocol. Select:OpenAI Completions

  Do not use an Anthropic or provider-specific protocol for this endpoint.
</Accordion>

<AccordionGroup>
  <Accordion title="No models are available">
    Check that:

    * the provider was saved successfully;
    * the Provider ID is `a2agent`;
    * the Base URL is correct;
    * the API key is valid;
    * at least one model was added; and
    * the model ID matches the current A2Agent model list.
  </Accordion>

  <Accordion title="The local Web UI does not open">
    Confirm that the process is still running and that port `3080` is not already in use.

    Try:

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

    If the terminal reports a JavaScript heap out-of-memory error while `npx` is starting the application, close other Node.js processes and retry with a larger Node.js heap:

    ```bash theme={null}
    export NODE_OPTIONS="--max-old-space-size=4096"
    npx @deepseek-ai/dsh web --no-open
    ```

    DeepSeek Harness is a local Web UI. It must remain running in the terminal while you access it from your browser.
  </Accordion>
</AccordionGroup>