AGENT / DEEPSEEK HARNESS

DeepSeek Harness

Configure DeepSeek Harness with Mengbi Router for personal terminal agent workflows.

!

Production integration docs · examples use router-api.mengbi-ai.net and a personal API key placeholder.

01 /

Prepare

Prepare DeepSeek Harness with a personal Mengbi Router key and a current model ID.

Prepare 1

  • Install the latest stable DeepSeek Harness release.
  • Create a personal Mengbi API key in the console.
  • Copy the exact model ID from the model catalog.

Prepare 2

Use the DeepSeek Harness configuration supported by your current installation.

bash
npm install -g @deepseek-ai/dsh
dsh --version
02 /

Configure

Connect DeepSeek Harness to the endpoint that matches its supported protocol.

Configure 1

Use the DeepSeek Harness configuration supported by your current installation.

bash
export OPENAI_API_KEY="sk-mengbi-xxxxxx"
export OPENAI_BASE_URL="https://router-api.mengbi-ai.net/v1"

Configure 2

Use the DeepSeek Harness configuration supported by your current installation.

NoteClient configuration fields can change between versions. Prefer the documented OpenAI-compatible or native provider setting.

03 /

Verify

Send a small request and check the key, endpoint, and model if it fails.

Verify 1

  • Install the latest stable DeepSeek Harness release.
  • Create a personal Mengbi API key in the console.
  • Copy the exact model ID from the model catalog.