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 24

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1035Memory & Context1312Coding & Developer Tools2813UI & Customization3666Integrations & Communication1920Vision & Media617Search & Research866Security & Access1264Models & Usage1681Productivity & Workflow2252

All plugins

1687 plugins
Lv0.1.0
dsh-llm-longcat

Llm Longcat

LongCat (LongCat-2.0) adapter for the DeepSeek Harness LLM seam — 1M context, thinking mode, tool calling

models-usage★ 2↓ 0
Updated 8/20/2026
Av0.1.1
@adverts13/dsh-auto-model-router

Auto Model Router

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

models-usage★ 2↓ 0
Updated 8/20/2026
Lv0.1.0
dsh-llm-governor

Llm Governor

Multi-model governance, routing, fallback, quota, and usage for DeepSeek Harness

models-usage★ 2↓ 0
Updated 8/20/2026
Lv0.1.1
dsh-llm-autorouter

Llm Autorouter

AutoRouter (model routing gateway / relay) LLM adapter for the DeepSeek Harness

models-usage★ 2↓ 0
Updated 8/20/2026
Pv1.5.8
dsh-plugin-wb2api-ui

Plugin Wb2api Ui

把本机 WorkBuddy / CodeBuddy 账号池接进 DeepSeek Harness：自托管网关进程并注册模型 provider、Web 设置面板（网关状态 / 每账号积分 / OAuth 登录 / 凭证导入 / 账号管理）、成长任务自动化引擎（一键确认待办 → 执行 → 达标自动领奖）。 · Bring a local WorkBuddy / CodeBuddy account pool into DeepSeek Harness: a self-supervised gateway process with model-provider registration, a sett

models-usagesecurity-access★ 1↓ 0
Updated 10/16/2026
Av0.1.5
@wisexin/dsh-antigravity

Antigravity

Google Antigravity / Cloud Code Assist model provider for DeepSeek Harness (DSH Desktop Beta Compatible)

models-usage★ 1↓ 0
Updated 10/16/2026
v0.0.1
@playform/hook-dsh-normalize-fullwidth

Hook Dsh Normalize Fullwidth

The fullwidth hook: a DeepSeek Harness plugin that hooks the llm/stream waterfall — the interceptable wrapper around EVERY streaming model call — and normalizes the full-width family (the entire FULLWIDTH FORMS range U+FF01–U+FF5E) in model output streams

models-usage★ 1↓ 0
Updated 10/16/2026
v0.1.0
dsh-ai-monitor

Ai Monitor

DeepSeek Harness plugin: query AI Monitor balance / usage from local SQLite — cost-aware agent, auto bookkeeping with the AI Monitor proxy.

models-usage★ 1↓ 0
Updated 10/16/2026
Ov1.0.0
@satanfire/opencode2dsh

Opencode2dsh

Use OpenCode Zen's anonymous free models in DSH (DeepSeek Harness): native LlmAdapter, no API Key required, zero runtime dependencies.

models-usage★ 1↓ 0
Updated 10/16/2026
Uv0.2.3
@sligqoer/dsh-usage-stats

Usage Stats

Usage statistics, provider quotas, model detection, and control plugin for DSH Desktop.

models-usage★ 1↓ 0
Updated 10/16/2026
v0.3.12
smart-compaction

Smart Compaction

dsh plugin: a compact_now tool letting the model trigger compaction itself at a safe point, plus a context_status tool so it can check real token usage against its context window, instead of only the automatic token-threshold trigger.

models-usage★ 1↓ 0
Updated 10/16/2026
Mv0.4.1
dsh-model-priority

Model Priority

Customize model/provider order: drag built-in DeepSeek family models within the card, and arrange the pi-ai family on the sidebar’s “Model Order” page (no conflict with the web-all model capabilities panel); the host’s model list follows this order (physically reorders the settings source of truth,

models-usage★ 1↓ 0
Updated 10/16/2026
Cv0.3.2
@guojinpeng/dsh-cost-meter

Cost Meter

DSH session and per-turn cost estimation plugin, supporting price synchronization with models.dev, OpenRouter, and DeepInfra, as well as custom per-model pricing. Configuration is located at ~/.dsh/guojinpeng/dsh-cost-meter/config.json.

models-usage★ 1↓ 0
Updated 10/16/2026
Cv0.8.4
dsh-codebuddy-auth

Codebuddy Auth

CodeBuddy (Tencent IOA) as a native DeepSeek Harness llm provider: browser OAuth login, token auto-renewal, credential storage, and /v3/config model sync.

models-usagesecurity-access★ 1↓ 0
Updated 10/16/2026
Tv2.1.0
dsh-token-quota

Token Quota

DeepSeek Harness usage monitoring: cycle limits, balances, reported costs, and local usage for today across 7 allowlisted providers (DeepSeek/OpenRouter/OpenCode/Command Code/Fireworks/OpenDesign); console sessions are separated from official HTTP methods, with the scope narrowed to a code-level fro

models-usage★ 1↓ 0
Updated 10/15/2026
Av0.4.7
dsh-advanced-provider-settings

Advanced Provider Settings

Advanced provider configuration UI for DeepSeek Harness (DSH): headers, User-Agent, retry policy, timeouts, vision, reasoning, transport and compatibility.

models-usage★ 1↓ 0
Updated 10/15/2026
Pv0.1.1
dsh-plugin-local-infer

Plugin Local Infer

DeepSeek Harness plugin that manages local inference engines (llama.cpp, NInfer, Hyper-Qwen, Strata): configure, size, launch, and publish a local engine as a DSH model. Installable bundle that mounts the localInfer service, engine providers, model-facing tools, and the Web UI as one profile layer.

models-usage★ 1↓ 0
Updated 10/15/2026
Kv0.2.0
dsh-key-usage

Key Usage

DeepSeek Harness sidebar “Usage”: displays usage details by channel, an activity heatmap, project/session usage, and official balance/quota (real-time preferred, falls back to snapshot on failure)

models-usage★ 1↓ 0
Updated 10/15/2026
Mv0.1.0
dsh-model-rotator

Model Rotator

Model auto-ranking and transparent failover for DeepSeek Harness: ranks discovered models by measured connectivity and speed, switches to the next candidate inside the same turn when the current one is unusable, and ships a grouped model list with per-channel switches. Never modifies model or provid

models-usage★ 1↓ 0
Updated 10/15/2026
Hv0.2.0-rc.7
dsh-handoff-compaction

Handoff Compaction

DSH context compression with visual token-budget settings: default 8k handoff + 16k recent context, adjustable for small-context models, with searchable full history

memory-contextmodels-usage★ 1↓ 0
Updated 10/15/2026
Cv0.1.2
dsh-cost-receipt

Cost Receipt

DeepSeek Harness plugin: one line under every reply showing what that exchange cost, plus the account and bonus balances. Peak/off-peak CNY pricing from real token usage. No network calls of its own, no storage.

models-usage★ 1↓ 0
Updated 10/15/2026
Wv1.6.2
dsh-where-did-my-tokens-go

Where Did My Tokens Go

DSH plugin: realtime token counter after the deep-thinking indicator

models-usageui-customization★ 1↓ 0
Updated 10/14/2026
Cv0.1.7
dsh-concurrency-meter

Concurrency Meter

Read-only model request concurrency monitoring for DeepSeek Harness

models-usage★ 1↓ 0
Updated 10/14/2026
Pv0.3.7
dsh-provider-probe

Provider Probe

Safe, explicit provider connectivity and latency checks for DeepSeek Harness

models-usage★ 1↓ 0
Updated 10/14/2026
Pv0.2.0-rc.11
dsh-providers-hub

Providers Hub

DeepSeek Harness plugin: one hub for AI coding providers — account login, multi-account pools, silent credential refresh, credit claiming, and a local OpenAI-compatible gateway

security-accessmodels-usage★ 1↓ 0
Updated 10/14/2026
Mv0.3.2
dsh-model-navigator

Model Navigator

Replace the official general model selector with global search, favorites, recently used, family navigation, and thinking intensity, reusing the official session model state

models-usage★ 1↓ 0
Updated 10/14/2026
Pv0.2.0
@swyc520/dsh-plugin-model-whitelist

Plugin Model Whitelist

DeepSeek Harness plugin: whitelist which models appear in the composer model selector. 在 DSH 的模型选择器里按模型勾选显示/隐藏，未勾选的模型不再出现在列表中。

models-usageui-customization★ 1↓ 0
Updated 10/14/2026
v0.1.1
@snnh/dsh-role-config

Role Config

Role presets and a model pool for dsh: role-routed delegation with capability conditions and priority fallback

agents-orchestrationmodels-usage★ 1↓ 0
Updated 10/14/2026
v1.0.2
dsh-wtq-pool

Wtq Pool

Connect the desktop logins for WorkBuddy, Trae, and Qoder on this machine to DeepSeek Harness. Automatically switch accounts when WorkBuddy is rate-limited. Each provider has its own toggle, with domestic and international options grouped separately.

models-usage★ 1↓ 0
Updated 10/14/2026
Pv0.2.1
dsh-peak-hours

Peak Hours

Run-window switch for DeepSeek Harness: run always, or only in off-peak hours — every task, including one already running, pauses when a China peak-price window starts and resumes when it ends.

models-usageproductivity-workflow★ 1↓ 0
Updated 10/14/2026
← Previous1…2223242526…57Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in