DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Models & Usage DSH plugins — Page 53

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All categories

All pluginsAgents & Orchestration1kMemory & Context1.3kCoding & Developer Tools2.8kUI & Customization3.7kIntegrations & Communication1.9kVision & Media615Search & Research865Security & Access1.3kModels & Usage1.7kProductivity & Workflow2.2k

All plugins

1670 plugins
Av1.0.0
dsh-ark-quota

Ark Quota

Show Volcengine Ark Coding Plan / Agent Plan quota in the DSH Web GUI: a side float panel + settings page, persistent credentials on disk, and periodic auto-refresh.

↓ 0★ 0
Updated 8/27/2026
Uv0.1.0
dsh-usage-board

Usage Board

Usage & cost dashboard plugin for DSH (DeepSeek Harness): per-session token metrics, 84-day heatmap, balance burn-down, and detail table with CSV export.

↓ 0★ 0
Updated 8/27/2026
Cv0.1.0
dsh-chatgpt-web

Chatgpt Web

ChatGPT Web primary-model bridge for DeepSeek Harness

↓ 0★ 0
Updated 8/27/2026
Pv0.1.2
@dockyard-dsh/plugin

Plugin

A macOS-only native account-pool and provider plugin for DeepSeek Harness.

↓ 0★ 0
Updated 8/26/2026
Bv1.0.2
dsh-balance-chip

Balance Chip

DeepSeek API balance in the DSH sidebar footer – live status dot plus amount, 60s refresh, key stays local.

↓ 0★ 0
Updated 8/26/2026
Av0.3.0
dsh-adaptive-effort

Adaptive Effort

DSH plugin: auto-select reasoning_effort (low/high/max) per user turn via a MiniMax complexity scorer with heuristic fallback, an effort-router-style token ledger, and a per-reply metadata label (model · effort · tokens · steps, click to jump back). Manual picker in the model popup; scorer triggers

↓ 0★ 0
Updated 8/26/2026
Lv0.1.0
dsh-llm-extra-retry

Llm Extra Retry

Extra model-request recovery for the DeepSeek Harness: retries a failed model request once after a fixed delay when the provider classifies the failure as PI_AI_ERROR (unrecognized upstream error text). All other error codes stay on the built-in dsh-llm-retry default policy (5 bounded exponential-ba

↓ 0★ 0
Updated 8/26/2026
Rv0.3.0
dsh-rename

Rename

Rename and filter provider groups and models in the DeepSeek Harness composer without changing their real routes.

↓ 0★ 0
Updated 8/26/2026
Pv1.0.0
dsh-poor-router

Poor Router

Budget-LLM pool router for DeepSeek Harness: usage ledger, health tracking, Thompson-sampling adaptive failover across free-tier models, quality tier ladder, executor pool, paid-guard, web panel + reroute badge. 穷鬼路由器。

↓ 0★ 0
Updated 8/26/2026
Iv0.1.0
@blue/dsh-image-model-router

Image Model Router

DeepSeek Harness plugin: route an agent request to a vision model (deepseek-v4-flash-vision-exp) when the user message contains an image, and keep the original model otherwise.

↓ 0★ 0
Updated 8/25/2026
Tv0.1.0
dsh-task-board-model

Task Board Model

Custom DSH task board fork with per-task provider, model, and reasoning-effort pins.

↓ 0★ 0
Updated 8/25/2026
Pv0.1.0
dsh-plugin-auto-continue

Plugin Auto Continue

Automatically continue failed DeepSeek Harness conversations: fallback model-request recovery plus bounded turn restarts

↓ 0★ 0
Updated 8/25/2026
Bv0.1.0
dsh-balance-vision

Balance Vision

DeepSeek real-time balance display plugin (including vision models): Displays the account balance and estimated cost of the current conversation in real time in the statistics bar below the input box in the dsh Web UI, with built-in official peak/off-peak pricing for deepseek-v4-flash / deepseek-v4-

↓ 0★ 0
Updated 8/25/2026
Fv0.1.0
fusion-symphony

Fusion Symphony

Multi-Model Fusion Orchestrator (MoA) over registered DeepSeek Harness LLM providers: conductor-led fan-out, evidence ledger, verify/synthesize loop, zero training.

↓ 0★ 0
Updated 8/25/2026
Cv0.5.0
dsh-custom-provider-settings

Custom Provider Settings

Global model request headers plus image input, reasoning, and DeepSeek system-role compatibility for custom providers

↓ 0★ 0
Updated 8/25/2026
Lv0.1.0
dsh-llm-quotes

Llm Quotes

LLM provider API price quotes in the dsh web sidebar

↓ 0★ 0
Updated 8/25/2026
v1.1.1
dsh-model-search-plugin

Model Search Plugin

DSH client plugin — keyword search when selecting models in the Web GUI

↓ 0★ 0
Updated 8/25/2026
Mv0.1.1
dsh-more-models-thinking-level

More Models Thinking Level

Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness

↓ 0★ 0
Updated 8/25/2026
Ov0.4.0
ox-alpha-dsh

Ox Alpha Dsh

Model Hub for DSH Desktop — a lightweight model/provider integration toolkit. Installs Ox Alpha (stealth/ox-alpha via OpenRouter) with one command and adds custom-model, custom-provider, health-check and model-discovery tools. 一个 DSH 插件：装好 Ox Alpha，并支持自定义模型/Provider 接入、健康检查与模型发现。

↓ 0★ 0
Updated 8/25/2026
Nv0.1.8
dsh-native-reasoning-slider

Native Reasoning Slider

A native, model-aware effort slider with polished light, dark, and per-model colors for DeepSeek Harness

↓ 0★ 0
Updated 8/25/2026
Bv1.1.0
dsh-balance-lite

Balance Lite

DSH web plugin: a draggable floating piggy-bank balance badge for the official DeepSeek API account balance, with per-conversation polling and a balance-deduction animation.

↓ 0
Updated 8/25/2026
Uv0.0.1
@dsh-external/dsh-usage-stats

Usage Stats

Usage statistics: aggregate total token usage and model distribution across all sessions, displayed on the settings page

↓ 0★ 0
Updated 8/25/2026
v1.0.2
dsh-qwen38-compaction-fix

Qwen38 Compaction Fix

DSH plugin: fixes compaction failure on local qwen3.8-27b gateways — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters

↓ 0★ 0
Updated 8/25/2026
Ov0.1.0
dsh-ocgo-quota

Ocgo Quota

OpenCode Go usage floating widget for the DeepSeek Harness Web UI: a bottom-right overlay showing rolling-5h / weekly / monthly quota, backed by the official opencode.ai usage endpoint.

↓ 0★ 0
Updated 8/24/2026
Sv0.1.0
dsh-session-caption

Session Caption

Two-phase session captioning for the DeepSeek Harness: instant keyword captions while the conversation is busy, budget-model refinement when it goes idle.

↓ 0★ 0
Updated 8/24/2026
Sv0.1.0
dsh-switch-cost

Switch Cost

Prices a dsh session against other models: what it cost on the route that ran it, and what the same token counts would have cost elsewhere.

↓ 0★ 0
Updated 8/24/2026
Tv0.1.5-beta
dsh-token-heatmap

Token Heatmap

Local Token heatmap in a separate settings section: week/month/quarter/year views + daily/weekly/monthly total statistics + Top 5 by model/provider

↓ 0
Updated 8/24/2026
Uv0.0.1
dsh-usage-dashboard

Usage Dashboard

DeepSeek usage and billing panel for DeepSeek Harness: balance, peak/off-peak pricing, and live countdown.

↓ 0
Updated 8/24/2026
Uv0.2.3
dsh-usage-stat

Usage Stat

Local-first usage dashboard for DSH Desktop: token usage, project activity, model distribution, recent sessions, and data health.

↓ 0★ 0
Updated 8/24/2026
Lv0.1.3
dsh-lmstudio-router

Lmstudio Router

Local LM Studio model router for the dsh web GUI: routes unimportant but token-expensive requests (bulk text work, compaction, session titles) to a local LM Studio model over its OpenAI-compatible /v1 endpoint, auto-launches LM Studio when it is not running, and fits every local request into the mod

↓ 0★ 0
Updated 8/24/2026
← Previous1…515253545556Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in