AI Agent Hub
Back to plugins
🤖

dsh-mode

Model Inference Updated 2026.08.20

Run the following command in DeepSeek Harness:

dsh plugin install uckkk/dsh-mode

Paste the following prompt into your AI chat to install this plugin:

Install the plugin by running dsh plugin install uckkk/dsh-mode in the DeepSeek Harness terminal; the source repository is at https://github.com/uckkk/dsh-mode .

About this plugin

dsh-mode is a lightweight model-inference plugin written entirely in Node.js with zero network dependencies. It targets scenarios where inference must run offline-in sandboxes, air-gapped machines, or CI pipelines-without spinning up external services or proxy layers.

Integration is minimal: once installed, the plugin registers tools that you invoke directly within a session. There is no server to configure, no additional runtime to manage, and no outbound connection required, keeping the dependency footprint as small as possible.

It suits developers who need local, self-contained inference, teams working inside network-restricted containers, or anyone who values a zero-dependency approach. Released under the MIT license, it is free to use, modify, and redistribute.

Use Cases

  • Run model inference in fully offline or air-gapped environments
  • Invoke inference tools inside network-restricted sandboxes or containers
  • Embed zero-external-dependency lightweight inference into CI pipelines

Best For

  • Solo developers who need fully local model inference
  • DevOps and platform teams running inference inside restricted containers
  • Developers who prefer zero network dependencies and minimal runtime overhead