When extending model inference capabilities in the DeepSeek Harness (DSH) ecosystem, some scenarios rely on external compute services. If local processing and offline availability are required, you can introduce dsh-goldbach.

Plugin Introduction

This plugin is maintained by uckkk and focuses on providing the “Goldbach decomposition” feature. It is implemented in pure Node.js, completes calculations locally, and does not involve network requests.

Core Features

  • Pure Node implementation: the core logic runs locally.
  • No network dependency: it remains available in offline environments after installation.

Installation and Activation

  1. Run the installation command:
    dsh plugin add github:uckkk/dsh-goldbach
  1. After installation, invoke the tool registered by the plugin in a DSH session.

Dependencies and Environment

The following dependency requirements must be met to run this plugin:

  • The version of @deepseek-ai/cordis must be ^4.0.1 or higher.
  • The version of @deepseek-ai/dsh-tools must be >=0.1.0-rc.6 or higher.

Notes

  • DSH plugins run with the permissions of the current process. Please check the source code and license before installation (this project uses the MIT license).

Summary

After installation, you can use the Goldbach decomposition feature in a local environment. For more information, see:
* GitHub Repository
* Plugin Directory