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.

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All categories

All pluginsAgents & Orchestration1.6kMemory & Context2.1kCoding & Developer Tools4kUI & Customization5.6kIntegrations & Communication3kVision & Media924Search & Research1.2kSecurity & Access1.8kModels & Usage2.5kProductivity & Workflow3.7k

All plugins

2457 plugins
Lv0.1.34
dsh-llm-commandcode

Llm Commandcode

Command Code Provider API LLM plugin for DeepSeek Harness

↓ 0★ 3
Updated 9/24/2026
Bv0.2.1
dsh-billing-balance

Billing Balance

DeepSeek Harness (dsh) model balance plugin: displays the official DeepSeek API balance, Volcengine Ark Coding/Agent Plan quota windows (5-hour/weekly/monthly), and reset countdowns.

↓ 0★ 3
Updated 9/19/2026
v0.1.1
dsh-opencode-go-model-list

Opencode Go Model List

Serve the live opencode Go model catalog from the harness's own built-in opencode-go provider route.

↓ 0★ 3
Updated 9/18/2026
Lv0.7.0
@webkubor/dsh-llm-hub

Llm Hub

Fills in the missing half of the official adapters on the DSH model page: gateway reachability checks, model catalog fetching, persistent DeepSeek balance display, and balance and quota cards for MiniMax / 智谱 / Moonshot / StepFun; it also registers locally installed codex / claude / agy as sub-agent

↓ 0
Updated 9/17/2026
Lv0.6.2
dsh-llm-hub

Llm Hubalt · webkubor

Fills in the missing half of the official adapter for the DSH model page: gateway reachability checks, model catalog fetching, persistent DeepSeek balance, and balance and quota cards for MiniMax / Zhipu / Moonshot / StepFun. No runtime dependencies and no changes to the DSH installation.

↓ 0
Updated 9/16/2026
v0.3.2
@xidong-ai/dsh-rate-limiter

Rate Limiter

DeepSeek Harness proactive rate-limiting plugin: limits by vendor token bucket, queuing excess requests with delays instead of failing

↓ 0★ 3
Updated 9/12/2026
v0.1.2
dsh-usage-lite

Usage Lite

Compact provider balances and local token-usage analytics for dsh web

↓ 0★ 3
Updated 9/10/2026
Lv0.1.17
@zhangyi/dsh-llm-ollama

Llm Ollama

Ollama native protocol (/api/chat) provider for DeepSeek Harness: llm-ollama settings namespace, serving LlmAdapter, /api/tags model discovery, and a whole-page Ollama settings section.

↓ 0★ 3
Updated 9/10/2026
Wv0.3.0
dsh-whale-widget-sankou

Whale Widget Sankou

DSH 小鲸鱼余额挂件·三口皮肤版 — Modified version based on dsh-whale-widget: customizable “三口” character appearance, status, sound effects, and transparency animations, including angry and overfull reminders, plus voice interaction

↓ 0★ 3
Updated 9/9/2026
Mv1.1.3
dsh-multi-candidate

Multi Candidate

Multi-candidate mode plugin (test-time scaling): 🐋 Configure via the floating ball panel (enable/number of candidates/second opinion/validation criteria; applies only to the current session). The model automatically runs a “parallel candidates → validation and selection” pipeline for tasks, without

↓ 0★ 3
Updated 9/7/2026
Lv0.7.1
dsh-liangwengu

Liangwengu

Liangwengu Reminder: alerts based on DeepSeek API peak and off-peak pricing periods (Beijing Time)—“run fast” before the peak and “open the valley” when the peak ends. Cartoon pop-up in the lower-right corner + browser system notifications + alert sounds.

↓ 0★ 3
Updated 9/4/2026
Ov0.1.1
dsh-opencode-go-autosync

Opencode Go Autosync

Sync opencode-go models from https://models.opencode.ai/api.json into llm-pi-ai provider opencode-go-autosync (one-click create/update in settings).

↓ 0★ 3
Updated 9/4/2026
Uv0.9.0
dsh-usage-ledger

Usage Ledger

DSH token usage & cost ledger: per-session aggregation, official multi-vendor pricing (peak/off-peak aware), budget control, cost-intelligence insights (projections, anomaly detection, health score, attribution), Prometheus metrics, SSE dashboard

↓ 0★ 3
Updated 9/1/2026
Rv0.2.0
dsh-route-resilience

Route Resilience

Multi-route high availability, fault isolation and observability for DeepSeek Harness. Route groups fail over between authorized provider routes on rate limits (429 / Retry-After), transport errors and auth/quota failures, with per-route quarantine (exponential backoff) and disablement.

↓ 0★ 3
Updated 8/29/2026
Bv0.1.0
@dsh-polyglot/bundle

Bundle

dsh-polyglot — the model switch for DSH: one generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek provider presets, and automatic provider fallback when a free tier rate-limits you

↓ 0★ 3
Updated 8/28/2026
Cv0.1.2
@necokeine/dsh-codex-relay

Codex Relay

Selectable Codex model provider for DeepSeek Harness over the local Codex app-server

↓ 0★ 3
Updated 8/28/2026
Pv0.2.0
dsh-peak-gate

Peak Gate

DeepSeek Harness peak/off-peak pricing gate: during peak hours (weekdays 09:00-12:00 / 14:00-18:00 Beijing time) every send asks for confirmation, with an option to mute the reminder for the current peak segment, or to queue the message for off-peak (half price) auto-send via the /peakgate command f

↓ 0★ 3
Updated 8/25/2026
v1.5.5
@hzjjxc/dsh-deepseek-console

Deepseek Console

DeepSeek account console: real-time balance monitoring / usage statistics / global floating HUD (direct connection to the official API; Key stored only in the local backend)

↓ 0
Updated 8/25/2026
Sv0.3.1
@momojie-s/dsh-subagent-model

Subagent Model

DSH plugin: a subagent delegation tool supporting per-call model routing and context inheritance, with clean context by default (same as built-in semantics); fresh_context: false forks the current conversation from the latest completed turn at the time of invocation (forked from @deepseek-ai/dsh-too

↓ 0★ 3
Updated 8/25/2026
Dv1.4.0
@local/dsh-deepseek-console

Deepseek Consolealt · @local

DeepSeek account console: real-time balance monitoring / usage statistics / global floating HUD (direct connection to the official API; Key stored only in the local backend)

↓ 0
Updated 8/25/2026
Ov0.1.0
dsh-opencode-models

Opencode Models

Manage OpenCode Zen free-tier and Go-tier models in settings.yaml: live model listings from opencode.ai, configured-versus-live drift per route, add/remove through four agent tools plus an OpenCode Models settings section.

↓ 0★ 3
Updated 8/24/2026
Pv0.1.1
dsh-plugin-auxiliary-runtime

Plugin Auxiliary Runtime

Cancelable auxiliary-model runtime for DeepSeek Harness with a provenance-preserving usage ledger outside official tokenUsage

↓ 0★ 3
Updated 8/22/2026
Lv0.1.0
luxueliu-usage-command

Luxueliu Usage Command

Luxueliu /usage command for DeepSeek Harness: per-day API spend card (by model × hour) from the local LiteLLM gateway log. Covers 3 billable model classes — official APIs (CNY + Beijing peak pricing), relay/OpenRouter APIs (USD), and plan pools (Cline/Token Plan, token-only) — all freely extensible

↓ 0★ 3
Updated 8/21/2026
Qv0.1.0
@samuflore/dsh-query-balance

Query Balance

DSH API balance checking tool

↓ 0★ 3
Updated 8/21/2026
Cv1.0.0
dsh-cost-tracker

Cost Tracker

Token cost tracking with per-model configurable pricing and peak/off-peak rates for the DeepSeek Harness

↓ 0★ 3
Updated 8/21/2026
Rv2.0.0
dsh-reconnect

Reconnect

Safe model-request retry for DeepSeek Harness with exponential backoff, model-availability recovery, and configurable unknown-error limits.

↓ 0★ 3
Updated 8/20/2026
Lv0.2.0
dsh-llm-guardian

Llm Guardian

Provider health, quota, account usage, and local model usage statistics for DeepSeek Harness

↓ 0★ 3
Updated 8/20/2026
Bv1.2.1
dsh-balance-ru

Balance Ru

Балансы провайдеров и расходы за день для DeepSeek Harness с пересчётом в рубли по курсу ЦБ РФ и русским интерфейсом плагина. Неофициальный форк @pipilu123566/dsh-balance.

↓ 0★ 2
Updated 11/4/2026
Mv2.26.0
model-failover-manager

Model Failover Manager

Model selection popup + routing groups: when a model fails, automatically switch to the next available model in the group and continue this round; also includes a data dashboard and free channel tab.

↓ 0★ 2
Updated 11/4/2026
Tv1.0.5
dsh-tri-model

Tri Model

Multi-model hierarchical collaboration: Planning → Execution → Review → automatic rework. Configure endpoints, protocols, models, and tiers in the settings panel.

↓ 0★ 2
Updated 11/4/2026
← Previous1…2324252627…82Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in