DeepSeek Harness Plugins · Model Inference
Plugins that extend DeepSeek Harness (DSH) with vision, workflows, memory, web tools and more.
dsh-mcp-apps is a dual-face Cordis plugin that enables DeepSeek Harness to act as an MCP Apps host, connecting to servers and rendering interactive apps.
Add vision capabilities to text-only DeepSeek Harness models by pasting images and getting text descriptions through a built-in VLM backend, without model switching.
The dsh-token-usage plugin adds a token usage statistics panel to DeepSeek Harness Web UI, displaying consumption by API, model, and date with animations and theme adaptation.
A DeepSeek Harness plugin that registers the subagent_model tool, exposing model routing and context inheritance as optional parameters beyond the built-in subagent.
A token-efficient persona runtime for DeepSeek Harness that reduces LLM token usage via local catgirl flavor rendering and tool schema pruning.
One line: after editing, type /simplify and the agent reviews only the lines you just changed — nothing else.
The dsh-llm-ollama plugin integrates Ollama Cloud into DeepSeek Harness, enabling chat, model discovery, and web search/fetch capabilities.
dsh-plugin-template is a verified community starting point for DeepSeek Harness plugins, with a CI that proves plugin tools are actually callable.
The dsh-models-dev-reasoning plugin automatically fills in missing reasoning efforts for third-party or custom models in DeepSeek Harness from models.dev, enhancing model inference configuration.
dsh-draw-router adds image generation to DeepSeek Harness as a universal router, enabling agents to draw images in chat with automatic model detection and multi-provider support.
A DeepSeek Harness plugin that uses an auxiliary LLM call to optimize prompts, featuring a Web UI button and automatic optimization for user messages to enhance model inference.
The dsh-vision-mix plugin combines text and vision models to enable image recognition, analysis, and generation for DeepSeek Harness Agents.