DeepSeek Harness Plugins · Model Inference
Plugins that extend DeepSeek Harness (DSH) with vision, workflows, memory, web tools and more.
A plugin that provides a token usage statistics panel for DeepSeek Harness, displaying cumulative totals, cache hit rates, activity heatmaps, and other visual data.
This plugin injects a fixed system-prompt section to ensure the agent always thinks and responds in Chinese, regardless of the user's language.
Integrate Gemini models from Google Antigravity accounts into DeepSeek Harness as a native LLM provider, supporting text generation, thinking, and tool calls.
Prompt for Me automatically suggests the next message as ghost text after a completed turn in DeepSeek Harness, without auto-submitting.
This plugin integrates free models from OpenCode Zen into dsh, supporting automatic syncing of model directories and free models for immediate use without configuration.
This plugin automatically injects reasoning effort settings and necessary parameters for custom model providers, enabling selection in the composer model selector.
A playable world-model toolkit for DeepSeek Harness that enables strip inspection, route identification, run scoring, and research loop iteration.
This DeepSeek Harness plugin provides a muapi_generate tool for unified access to over 100 image, video, audio, and 3D generation models through MuApi.
dsh-argp is a context compression engine based on atomic reference graph pruning, achieving zero LLM calls through logical chain decision-making for selective forgetting.
A text adventure preset for DeepSeek Harness, offering nineteen world entries where the model outputs only novel text for immersive story creation.
dsh-llm-codex plugin integrates ChatGPT Codex with DeepSeek Harness, supporting OAuth login, model catalog, optional search and image generation, and remote settings management.
A DSH model proxy plugin that routes LLM requests by target domain, sending selected models through a proxy while others connect directly, with automatic retry on failure.