DeepSeek Harness Plugin Hub

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All plugins

874 plugins
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

models-usage00
Updated 8/25/2026
v2.1.0
dsh-thinking-levels-settings

Thinking Levels Settings

Persistent per-model thinking-level settings for custom DSH providers (official dsh client-plugin form)

models-usage00
Updated 8/25/2026
v0.4.0
dsh-llm-pi-ai-headers

Llm Pi Ai Headers

DeepSeek Harness LLM User-Agent/header injector with key pool round-robin: keeps the official llm-pi-ai adapter, re-injects user-agent, and supports multi-key rotation per provider. | DeepSeek Harness LLM 请求头注入器 + Key 轮询:保留官方适配器,补回 User-Agent,支持按提供商多 Key Round-Robin 轮询。

security-accessmodels-usage00
Updated 8/25/2026
v0.1.0
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.

models-usageui-customization00
Updated 8/24/2026
v0.1.4
dsh-llm-subscription

Llm Subscription

Native DeepSeek Harness LLM adapter for Claude Code / Antigravity CLI subscriptions, plus local Ollama — Claude, Gemini and a free local model in the model picker, no API key

models-usageintegrations-communication00
Updated 8/24/2026
v0.1.0
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.

memory-contextmodels-usage00
Updated 8/24/2026
v0.1.0
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.

models-usage00
Updated 8/24/2026
v0.1.0
@davidgallo/dsh-llm-subscription

Llm Subscriptionalt · @davidgallo

Native DeepSeek Harness LLM adapter for Claude Code / Antigravity CLI subscriptions — Claude and Gemini in the model picker, no API key

models-usage00
Updated 8/24/2026
v0.1.5-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

models-usageui-customization0
Updated 8/24/2026
v0.2.3
dsh-usage-stat

Usage Stat

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

models-usageui-customization00
Updated 8/24/2026
v0.1.3
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

models-usage00
Updated 8/24/2026
v0.6.0
dsh-usage-billing

Usage Billing

DeepSeek Harness usage and cost statistics plugin: billed according to peak and off-peak prices before and after the 2026-08-17 price adjustment, with a main interface summary panel, session-level details, and charts

models-usageui-customization00
Updated 8/24/2026
v0.1.0
dsh-model-ocean-selector

Model Ocean Selector

A DeepSeek Harness plugin with a vertical model list and an animated Three.js particle reasoning-effort control.

models-usageui-customization00
Updated 8/24/2026
v0.1.2
dsh-model-gate

Model Gate

Single-model disable gate: hides denied models from every discovery path, blocks dispatch with an in-protocol error chunk, and exposes a settings-section UI for the denylist

security-accessmodels-usage00
Updated 8/24/2026
v0.2.0
dsh-token-viewer

Token Viewer

CC Switch-style token consumption statistics for the DeepSeek Harness Web GUI: per-request usage log, real-consumption hero, request-time-bucketed trend chart, per-model peak/off-peak list pricing, per-project and per-model stats, and account balance.

models-usageui-customization00
Updated 8/24/2026
v0.1.0
dsh-usage-cost

Usage Cost

Real-time DeepSeek token usage and cost meter: a status-bar capsule plus detail panel driven by a session projection, with local-only today/month/model cost persistence.

models-usage00
Updated 8/24/2026
v0.1.2
@yyfather/dsh-balance

Balance

DeepSeek Harness balance and spending plugin: displays DeepSeek/MiMo balances and spending in the status bar (this session/current activity/recent request/previous conversation), prices each request by model and peak/off-peak period, and supports spending limit alerts (click to configure)

models-usageui-customization00
Updated 8/24/2026
v1.3.4
dsh-calculator

Calculator

DeepSeek Harness web plugin: DeepSeek API spend (per session / all sessions) and account balance in a top-right overlay card. Only deepseek-official routes are billed; third-party models are reported as unbilled.

models-usageui-customization00
Updated 8/24/2026
v0.1.0
dsh-plugin-openai-api

Plugin Openai Api

OpenAI-compatible /v1/chat/completions (streaming and non-streaming) and /v1/models endpoint on the DSH web server: one DSH agent session per request user field.

integrations-communicationmodels-usage00
Updated 8/24/2026
v0.2.0
@flowingboy/dsh-local-perf

Local Perf

Durable DeepSeek Harness bundle: the local-model performance tuning carried as a re-installable plugin layer (compaction, tool-result pruning, time context, cloud title routing, text-toolcall guard) — survives dsh updates

models-usagedeveloper-tools00
Updated 8/24/2026
v0.1.1
dsh-local-llm

Local Llm

DeepSeek Harness plugin for local GGUF models without Ollama

models-usage00
Updated 8/24/2026
v0.2.0
dsh-peak

Peak

DeepSeek API peak/off-peak pricing indicator: a live composer pill (red during peak, green off-peak) with a countdown to the next switch, plus a dsh_peak_status tool the agent can call to warn about cost.

models-usageui-customization00
Updated 8/24/2026
v0.1.0
dsh-oauth-copilot

Oauth Copilot

GitHub Copilot OAuth provider and model adapter for DeepSeek Harness

models-usagesecurity-access00
Updated 8/23/2026
v0.1.0
@maimu/dsh-balance

Balancealt · @maimu

DeepSeek Harness balance and spending plugin: displays DeepSeek/MiMo balances and spending in the status bar (this session/current active session/most recent/previous conversation), calculates pricing per request based on model and peak/off-peak periods, and supports spending threshold alerts (click

models-usageui-customization00
Updated 8/23/2026
v1.0.0
dsh-ua-headers

Ua Headers

Customize the User-Agent and additional request headers used when calling the selected model, with a control panel provided on the settings page.

models-usageui-customization00
Updated 8/23/2026
v0.3.5
dsh-plugin-quota-monitor

Plugin Quota Monitor

DSH sidebar footer quota & balance monitor with a Settings section (设置→插件管理): always-on DeepSeek Rage (¥), plus per-provider status rows — OpenCode Go HP/MP/SP (monthly/weekly/5h) and SCNet (国家超算) Credits remaining estimated locally from DSH session logs. Provider selectable (auto/opencode/scnet), m

models-usageui-customization00
Updated 8/23/2026
v1.0.1
dsh-agent-team-gui

Agent Team Gui

Persistent multi-model squads for DeepSeek Harness with durable orchestration, DAG workflows, run history, and provider-reported token usage

agents-orchestrationmodels-usage00
Updated 8/23/2026
v0.1.5
dsh-opencode-go-models

Opencode Go Models

DSH plugin to sync opencode-go model catalog with precise multi-modal support

models-usagevision-media00
Updated 8/23/2026
v0.1.1
@wangyong1972/dsh-quota-dashboard

Quota Dashboard

Draggable quota/cost dashboard for the dsh web GUI: combines OpenRouter and DeepSeek balances and spend (official APIs + local ledger) in one movable card.

models-usageui-customization00
Updated 8/23/2026
v0.4.0
dsh-openai-server-compaction

Openai Server Compaction

OpenAI Responses adapter and durable server-side compaction bundle for DeepSeek Harness.

models-usage00
Updated 8/23/2026