DSH插件商店

dsh-collapsible-models

ZhenXifu

该仓库暂未提供项目说明。

dsh-provider-auto

icekale

Automatically add reasoning-level controls to compatible DeepSeek Harness provider models

dsh-gpu-monitor-nvml

janpauldahlke

DeepSeek Harness (dsh) plugin: live NVIDIA GPU monitor in the web rightbar. NVML-first on Linux (nvidia-smi fallback). NVIDIA only! Not AMD/Intel/macOS. Multi-GPU util/VRAM/power/temp, processes, sparklines. Installable dsh.bundle.

dsh-mindseye

kanchengw

Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, and GUI automation, through layered evidence memory and cache.

dsh-handoff-compaction

knighthongyu

Context compression for DSH: visually configure summary and recent-context budgets (8k + 16k by default), keep tasks on track, and search full conversation history. Friendly to small-context models.

dsh-malko-prefs

malko

Add some settings to make deepseek harness more comfortable to use, compaction thinking mode and tresholds, llama models enrichment, web notifications

dsh-reasoning-level

peterwangze

DSH (DeepSeek Harness) plugin: unified default reasoning level (thinking effort) for all models — per-model defaults with capability probing, live call statistics, one-command install via dsh plugin

dsh-gpu-cleanup

princepainter

DeepSeek Harness Web UI plugin: adds a 'Release GPU' button to free VRAM by unloading local Ollama models

dsh-visual-aid

shenyan-008

dsh visual aid plugin: lets text-only main models handle images via a vision model

dsh-capability-inspector

tree201

DeepSeek Harness Doctor and DSH runtime diagnostics for tools, models, skills, workspaces, sessions, plugins, and MCP troubleshooting

dsh-LLM-quotes

v587d

Latest LLM provider API prices, right inside DeepSeek Harness (dsh) → Settings → Models.最新的大模型（LLM）厂商 API 价格，直接显示在 DeepSeek Harness（dsh） 的 设置 → 模型 页面中。

computer-user-vision

xie129716

Unofficial fork of computer-user: fixes the silent load failure on DSH >= 0.1.2, and returns screenshots as real images to vision models with an exact image->screen coordinate mapping.

dsh-plugin-effort-declare

zimodzh

为手工 OpenAI 兼容模型补上推理档位声明的 DSH 插件 / DSH plugin to declare reasoning efforts on hand-added OpenAI-compatible models.

tolten-image-attach

EmmanuelMartinez

Attach an image to the DeepSeek Harness composer and the session model switches itself to a vision model — then restores your previous model when the image is removed. Material Design 3 button, native file picker, thumbnails. MIT.

dsh-cost

GalileoNio

A DeepSeek Harness plugin: per-segment Session cost in the composer statistics strip, priced from the harness model catalog (41 providers, ~1495 models).

s1cap

Jaffe2718

System-1 decision models (Jev/Laya/Kev-class) as the governance layer for an LLM agent context lifecycle: growing association graph over session segments, relevance-gated recall with Trace-as-State ordering, and plan pre-ranking — measured in solve rate, cache hit/miss tokens, cost and latency. DSH plugin + harness-agnostic proxy.

dsh-plugin-glm-vision

baldovinmarques391-design

GLM Vision plugin for DSH: image translation for non-multimodal models via GLM-4V-Flash

dsh-image-bridge

hZsFN

Image message bridge for text-only models in DeepSeek Harness (dsh): image blocks → text placeholder + local path, vision via qwen script

dsh-gateway-models

itchenshi

DeepSeek Harness plugin for gateway routes: declares the OpenCode Go and Command Code route protocol + endpoint (so the API address never has to be typed) and completes their model lists. The OpenCode Go half puts DeepSeek V4.1 first; the Command Code half syncs all 81 models from its public catalog. Also adds the x-opencode-session header.

dsh-plugin-model-config

liutian11451-png

Full model-configuration editor for the DeepSeek Harness web Settings > Models page: every field the deployment's model-config schema declares.

dsh-models-filter

odelbos

DeepSeek Harness plugin used to add an input filed to filter the models menu. (with arrow up/down + enter)

dsh-tabbit-brain

wbdxy

DeepSeek Harness subagent provider: delegate reasoning to Tabbit-served models through a local gateway. Ships its own minimal preset, gateway management, and delegation guidance.