dsh-ai-models
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-ai-models
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-ai-models in DeepSeek Harness to install this plugin, with the source repository at https://github.com/uckkk/dsh-ai-models
About this plugin
AI model entries in a DeepSeek Harness session can be scattered across configs and registries, making manual lookups slow and error-prone. dsh-ai-models condenses this into two lightweight tools: list_aimodel pulls the full inventory of available models in one call, and get_aimodel fetches detailed fields for a specific entry by ID or name, giving you a quick overview-to-detail workflow.
The plugin is written in pure Node.js with zero external network calls. It boots instantly and runs reliably in offline sandboxes, CI pipelines, or air-gapped environments where network instability or missing credentials would otherwise be a problem.
If you are building multi-model inference pipelines on DeepSeek Harness and need to verify model parameters, confirm registration status, or expose a structured model-query interface to a higher-level agent, dsh-ai-models is a thin, fast foundation layer that just gets out of the way.
Use Cases
- Quickly browse the inventory of available AI models in a session
- Look up detailed registration fields for a specific model by ID or name
- Query model entries reliably in offline sandboxes or air-gapped environments
Best For
- Developers building multi-model inference pipelines on DeepSeek Harness
- Engineers validating model registration in CI or air-gapped environments
- Architects exposing structured model query interfaces to higher-level agents
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.