DeepSeek Harness Plugin Hub

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All plugins

876 plugins
v0.1.27
@dsh-external/dsh-cost-guard

Cost Guard

成本守卫: A cost-saving plugin for DeepSeek V4-Flash-0731 pure API pricing—calculates session costs, cache hit rates, and the amount saved with full cache hits according to the official peak/off-peak tiers dated 2026-08-17 (peak: 09:00-12:00 / 14:00-18:00); ¥ budget guard (budget = hard limit: once the

models-usageproductivity-workflow20
Updated 8/21/2026
v0.1.1
dsh-model-accordion

Model Accordion

Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.

ui-customizationmodels-usage20
Updated 8/21/2026
v0.1.0
@local/dsh-advanced-model-editor

Advanced Model Editor

Advanced model configuration page for DSH WebUI

models-usage20
Updated 8/20/2026
v0.2.0
dsh-llm-web-bridge

Llm Web Bridge

DSH web plugin: bridge to third-party web LLMs (Gemini, ChatGPT, Doubao, custom) — agent-driven consult_llm tool with review/code-review/adversary/verify roles, text-log primary UI with on-demand live view, named sessions, token metering, headed/headless browser daemon.

integrations-communicationdeveloper-toolsmodels-usage20
Updated 8/20/2026
v0.4.0
dsh-budget-guard

Budget Guard

DeepSeek Harness plugin: LLM cost metering with budget enforcement (deny/warn), peak-valley pricing and a live usage dashboard

models-usageui-customization20
Updated 8/20/2026
v0.1.0
dsh-llm-longcat

Llm Longcat

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

models-usage20
Updated 8/20/2026
v0.1.1
@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-usage20
Updated 8/20/2026
v0.1.0
dsh-llm-governor

Llm Governor

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

models-usage20
Updated 8/20/2026
v0.1.0
dsh-usage-guard

Usage Guard

DSH usage statistics plugin: token collection, activity heatmap, cost estimation, over-limit guard

models-usage20
Updated 8/20/2026
v0.1.1
dsh-llm-autorouter

Llm Autorouter

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

models-usage20
Updated 8/20/2026
v0.3.9
dsh-token-usage-stats

Token Usage Stats

DSH web plugin: cross-session token usage, request count, and optional cost analytics (ctx.tokenUsageStats), with a self-contained dashboard page and a sidebar footer entry.

models-usageui-customization10
Updated 9/4/2026
v0.15.1
dsh-company

Company

Decision-driven AI company orchestration with HR governance, monetary budgets, model discovery, and deterministic audit for DeepSeek Harness

agents-orchestrationsecurity-accessmodels-usage10
Updated 9/4/2026
v0.1.4
dsh-plugin-cost

Plugin Cost

DeepSeek Harness cost tracker: per-turn & total token usage and billing (DeepSeek pricing, peak/off-peak aware), rendered in the chat UI.

models-usageui-customization10
Updated 9/4/2026
v0.3.2
@taylorswitiger/dsh-plan-bridge

Plan Bridge

Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.

models-usageintegrations-communication10
Updated 9/4/2026
v0.1.7
dsh-minimax-usage

Minimax Usage

Show MiniMax Token Plan subscription usage in the DSH Web UI

models-usageui-customization10
Updated 9/4/2026
v0.3.10
dsh-router-traework

Router Traework

DSH plugin: TRAE SOLO supplier for dsh-router. Provides the traework supplier (free SOLO chat channel, ported from traework2api) to dsh-router through the router.suppliers cordis service.

models-usageintegrations-communication10
Updated 9/4/2026
v0.1.0
@ycp424c/dsh-luna-vision-bridge

Luna Vision Bridge

DSH LLM adapter that transcribes native image attachments with Codex Luna before delegating to DeepSeek

vision-mediamodels-usage10
Updated 9/4/2026
v0.2.0
dsh-tool-lipsync

Tool Lipsync

FreeLipSync lip-sync talking video panel — an embedded DSH interface panel for uploading, text, audio, model selection, free generation, and recent generations. No Key or login required; does not consume model tokens.

models-usage10
Updated 9/4/2026
v0.1.6
dsh-ollama-usage

Ollama Usage

DeepSeek Harness 插件:可视化 Ollama Cloud 账号用量余量(每 5 小时会话用量 + 周用量),支持侧边栏双横条、设置页面板、API Key 与用量快照持久化、自动刷新与登录引导。Ollama Pro usage & remaining-quota visualization for DeepSeek Harness: 5-hour session + weekly quota bars in the sidebar footer, a full settings panel, persisted API key and usage snapshots, auto-

models-usageui-customization10
Updated 9/4/2026
v0.3.1
dsh-plan-bridge

Plan Bridgealt · TaylorSwitiger

Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.

models-usageintegrations-communication10
Updated 9/4/2026
v1.2.3
dsh-kimi-subscription

Kimi Subscription

Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route

models-usagesecurity-access10
Updated 9/3/2026
v0.2.0
dsh-token-optimizer

Token Optimizer

Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness

models-usagedeveloper-tools10
Updated 9/3/2026
v0.3.8
dsh-llm-grok

Llm Grok

xAI Grok subscription login and chat for DeepSeek Harness

models-usage10
Updated 9/3/2026
v0.1.18
dsh-llm-commandcode

Llm Commandcode

Command Code Provider API LLM plugin for DeepSeek Harness

models-usage10
Updated 9/3/2026
v0.3.0
dsh-claude-driver

Claude Driver

DSH host plugin: drive the main session model through local Claude Code (official Claude Agent SDK) by taking over the llm/stream route `claude-code`.

models-usagedeveloper-tools10
Updated 9/3/2026
v0.2.0
dsh-web-search-zai

Web Search Zai

Z.ai and Zhipu web search for DeepSeek Harness, with Coding Plan MCP quota, REST API billing, and bilingual settings.

search-researchintegrations-communicationmodels-usage10
Updated 9/3/2026
v0.4.0
dsh-model-fallback

Model Fallback

DeepSeek Harness plugin: pick configured model providers, and when a model fails with a model-related error the request automatically falls through the provider group's models (then the next selected provider) until one works, so the unfinished task keeps going. Adds its own Settings tab.

models-usage10
Updated 9/3/2026
v0.2.0
dsh-token-speed

Token Speed

DSH web plugin: a draggable ring-gauge dashboard pinned to the bottom-right that shows live model output speed (tok/s), with an expandable detail panel (per-step exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).

models-usageui-customization10
Updated 9/3/2026
v0.2.0-alpha.1
deepseek-openai-codex

Deepseek Openai Codex

Configuration-only DeepSeek Harness bundle that enables the built-in Pi-backed OpenAI Codex route

models-usage10
Updated 9/2/2026
v0.2.1
@ddtcorex/dsh-maestro-observe

Maestro Observe

Maestro observe — trace/health/cost debug tooling (Phase 3)

models-usagedeveloper-tools10
Updated 9/2/2026