AI Agent Hub
Back to plugins
🤖

dsh-min

Model Inference Updated 2026.08.20

Run the following command in DeepSeek Harness:

dsh plugin install uckkk/dsh-min

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

Run dsh plugin install uckkk/dsh-min in DeepSeek Harness to install the plugin; the full source code is available at https://github.com/uckkk/dsh-min.

About this plugin

Many model-inference plugins lean on network requests or heavyweight runtimes, adding deployment friction and debugging overhead. dsh-min tackles that pain point by providing a minimal, self-contained entry point for inference tooling so that in-session model calls stay free of external services or tangled dependency chains.

The design boils down to two keywords: pure Node and zero network dependency. The entire plugin is written in vanilla Node.js with no HTTP client, no third-party networking library, and no background service to launch. Once installed, the plugin registers its inference tools directly into the current session, ready to call on demand with no extra configuration.

It is a strong fit if you are building offline-first, zero-dependency workflows or need inference calls inside constrained environments such as CI pipelines, edge devices, and air-gapped machines. Rather than stacking features, dsh-min keeps the surface area intentionally small and lets you focus on what the model actually needs to do.

Use Cases

  • Invoke model-inference tools in an offline or intranet environment
  • Register inference tools in CI pipelines without any network access
  • Lightweight inference tooling on edge devices or sandboxed runtimes

Best For

  • Developers building offline-first workflows
  • Engineers deploying models in constrained or air-gapped environments
  • Pure Node.js practitioners who prefer zero external dependencies