dsh-power-mod
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-power-mod
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-power-mod in the DeepSeek Harness terminal to install this plugin; the source code is available at https://github.com/uckkk/dsh-power-mod .
About this plugin
dsh-power-mod (Mo Power) is a lightweight model-inference plugin whose defining trait is a pure Node.js implementation with zero network dependencies.
The design philosophy is straightforward: it packages model-inference capability into registered tools that you invoke right inside your conversation. The entire runtime chain stays within a local Node environment, so no outbound API calls or remote resource downloads are needed. That makes it a natural fit for offline, intranet, or network-restricted setups.
Who is it for? If you need a local model-inference capability in constrained environments, or simply prefer a self-contained inference pipeline that does not lean on any third-party service, dsh-power-mod is a sufficiently lightweight option. Install it, call its registered tools in conversation, and you are running with no extra configuration overhead.
Use Cases
- Local model inference in fully offline environments
- Self-contained inference in restricted intranet settings
- Autonomous inference pipelines without any external API calls
Best For
- Developers who need model inference in offline or intranet environments
- Teams that prefer a fully autonomous, third-party-free inference pipeline
- Solo developers seeking a lightweight, zero-config inference experience
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.