dsh-frontend-mobile
Run the following command in DeepSeek Harness:
dsh plugin install satan9394/dsh-frontend-mobile
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness by running dsh plugin install satan9394/dsh-frontend-mobile; the full source code is available at https://github.com/satan9394/dsh-frontend-mobile .
About this plugin
dsh-frontend-mobile is a mobile-device frontend plugin for the DeepSeek Harness ecosystem, classified under the model-inference track. It tackles a straightforward problem: making Harness model-inference capabilities accessible from mobile browsers, bridging the experience gap that exists beyond desktop.
Based on its name and category, the plugin focuses on mobile UI adaptation and the front-end interaction layer, offering a small-screen-tailored interface for initiating inference requests and displaying results. The README has yet to expand on further technical details, and the project is still in its early stages, but the MIT license lowers the barrier for integration and secondary development.
If you are building a model-inference service that needs to reach users across multiple form factors, or simply want to call models through Harness on a phone or tablet, this plugin is worth keeping on your radar.
Use Cases
- Invoking Harness model-inference services from a mobile browser
- Small-screen UI adaptation for inference requests and results
- Extending desktop model-interaction capabilities to mobile devices
Best For
- Front-end developers needing a mobile inference entry point
- Integration engineers building cross-platform AI applications
- Technical teams exploring mobile extensions in the Harness ecosystem
Related Plugins
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.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.