🎉 Launch offer — limited time 🔥
ModelGo
ModelGo
Get Started

DeepSeek Harness

DeepSeek Harness (DSH) is an open-source agent framework from DeepSeek AI. It combines models, tools, filesystems, terminals, sessions, and a Web UI into a runnable agent. Add a custom provider to call models through ModelGo's OpenAI-compatible API.

Before you start

  • Install Node.js 22 or later.
  • Install pnpm 11 or later.
  • Create an API key in the ModelGo Console.
  • Confirm a logical model name allowed for the API key in the Model Catalog.

1. Install and start DeepSeek Harness

The current source-install path is:

bash
git clone https://github.com/deepseek-ai/deepseek-harness.git
cd deepseek-harness
pnpm install
pnpm run build
pnpm dsh web
Start DeepSeek Harness from source

The terminal prints the Web UI address. The default is http://127.0.0.1:3080; use the address printed by your terminal if the port is already in use.

For a quick preview, you can also run:

bash
npx @deepseek-ai/dsh web

2. Configure ModelGo

Open the address printed by the terminal, click the sidebar button in the upper-left corner, and then click Settings.

Open DeepSeek Harness settings

Select Models and click Add custom provider.

Add a custom provider

Use these values:

SettingValue in ModelGo
Provider IDmodelgo
Display nameModelGo
API URLhttps://api.modelgo.ai/v1
API protocolopenai-completions
API keyModelGo API key
Model IDA logical model name from the Model Catalog
Display nameYou can use the same value as the model ID
Fill in the ModelGo custom provider

Click Create provider to save the configuration. Keep these points in mind:

3. Start a session

Return to the main view, choose a workspace, and then select the ModelGo model you just added.

Select the ModelGo model

Send a simple task such as “Describe this project in three sentences.” A normal response confirms the ModelGo connection.

Troubleshooting

The Web UI does not open

Make sure pnpm dsh web is still running and open the port printed by the terminal. The default is 3080; DSH may choose another port when it is occupied.

401 or authentication failed

Check that the API key is complete, has no extra spaces, and was created in the ModelGo Console.

403 or model unavailable

Confirm that the model ID is a logical ModelGo model allowed by the policy attached to the API key.

404 or incorrect endpoint path

Set the API URL to https://api.modelgo.ai/v1, not a full /chat/completions URL. Select openai-completions as the API protocol.

The model list is empty

Check that a model ID is present and that the custom provider was saved. You can verify the ModelGo endpoint first:

bash
curl https://api.modelgo.ai/v1/models \
  -H "Authorization: Bearer $MODELGO_API_KEY"

Related docs