DeepSeek Harness Plugin Hub

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All plugins

876 plugins
v0.5.0
dsh-billing-glass

Billing Glass

Liquid-glass billing overlay for the DeepSeek Harness Web GUI: provider balances, session cost, daily spend and token buckets. DeepSeek-first with an extensible provider registry.

models-usageui-customization30
Updated 8/27/2026
v0.1.19
dsh-kiro

Kiro

Kiro provider for DeepSeek Harness with multi-method login, usage, model controls, and token/profile refresh

models-usagesecurity-access30
Updated 8/25/2026
v0.2.0
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

models-usage30
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)

models-usageui-customization30
Updated 8/25/2026
v0.3.1
@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

agents-orchestrationmemory-contextmodels-usage30
Updated 8/25/2026
v1.4.0
@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)

models-usageui-customization30
Updated 8/25/2026
v0.2.1
dsh-balance-stats

Balance Stats

Community balance and spend statistics plugin for DeepSeek Harness Web, with session usage and optional auto-imported invoice summaries.

models-usage30
Updated 8/24/2026
v0.1.2
@dsh-external/dsh-llm-retry-settings

Llm Retry Settings

LLM automatic retry settings card: modify the retry count (maxRetries) and backoff times (initialDelayMs/maxDelayMs/jitterRatio) in Settings → General; takes effect in real time for the dsh-llm-retry host

models-usage30
Updated 8/24/2026
v0.2.0
dsh-deepseek-monitor-moyuer233

Deepseek Monitor Moyuer233

DeepSeek usage monitor as a DeepSeek Harness (DSH) plugin: balance / day-month-all-time token & cost panels in the chat UI with drag-reorder config, plus an optional local usage proxy

models-usageui-customization30
Updated 8/24/2026
v0.1.1
dsh-usage-lite

Usage Lite

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

models-usageui-customization30
Updated 8/24/2026
v0.1.19
dsh-go-usage

Go Usage

DeepSeek Harness plugin: OpenCode GO plan usage (three-window quota + DSH token/spend statistics by model + input-box mini bar)

models-usagedeveloper-tools30
Updated 8/24/2026
v0.6.3
dsh-billing-community-bundle

Billing Community Bundle

Installable DeepSeek Harness bundle for the dsh-billing host projection and client UI

models-usageui-customization30
Updated 8/22/2026
v0.1.21
dsh-account-usage

Account Usage

DeepSeek Harness web-GUI plugin: a Settings「账户」page showing DeepSeek platform balance/usage (daily cost chart, per-model requests & tokens, selectable time range) and the OpenCode Go 5h/weekly/monthly quota with reset times.

models-usageui-customization30
Updated 8/22/2026
v1.0.0
dsh-token-stats

Token Stats

DSH plugin: token usage & cost statistics per model / date / session with history backfill and CSV/JSON export

models-usage30
Updated 8/22/2026
v0.1.1
dsh-plugin-auxiliary-runtime

Plugin Auxiliary Runtime

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

models-usage30
Updated 8/22/2026
v0.3.1
@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

models-usage30
Updated 8/21/2026
v0.2.0
@local/dsh-ui-model-selection-collapsible

Ui Model Selection Collapsible

DSH composer model seat with accessible per-provider collapsible groups.

models-usageui-customization30
Updated 8/21/2026
v0.1.0
@samuflore/dsh-query-balance

Query Balance

DSH API balance checking tool

models-usage30
Updated 8/21/2026
v1.1.2
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

models-usage30
Updated 8/21/2026
v0.5.3
dsh-cursor-subscription

Cursor Subscription

Cursor subscription for DeepSeek Harness with browser login, token refresh, model discovery, and the Cursor Agent chat protocol

models-usageintegrations-communication30
Updated 8/21/2026
v1.0.0
dsh-cost-tracker

Cost Tracker

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

models-usage30
Updated 8/21/2026
v2.0.0
dsh-reconnect

Reconnect

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

models-usage30
Updated 8/20/2026
v0.1.5
@deepseek-ai/dsh-plugin-usage

Plugin Usage

Usage (用量) deployment plugin for DeepSeek Harness (DSH): a real-time token & cost dashboard tab next to chat/trajectory, with live streaming estimates, DeepSeek official peak/off-peak pricing and OpenCode Go plan pricing, custom price table, and CSV/JSON export.

models-usage30
Updated 8/20/2026
v0.2.0
dsh-llm-guardian

Llm Guardian

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

models-usage30
Updated 8/20/2026
v0.1.7
dsh-cliproxyapi-provider

Cliproxyapi Provider

CLIProxyAPI provider for DeepSeek Harness with local auto-discovery, dynamic model sync, model switching, and vision preprocessing.

models-usageintegrations-communication30
Updated 8/20/2026
v1.2.0
dsh-connect-trae

Connect Trae

Connect locally signed-in Trae models to DeepSeek Harness, plus a read-only usage/credits summary.

integrations-communicationsecurity-accessmodels-usage20
Updated 9/4/2026
v2.0.2
dsh-local-llm-controller

Local Llm Controller

DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and one shared DSH provider carrying both slots' models with four thinking-ef

models-usage20
Updated 9/4/2026
v0.1.0-rc.5
@deepseek-ai/dsh-llm-acp

Llm Acp

ACP LLM adapter + ACP Servers settings UI: drives external Agent Client Protocol servers as model providers on the DeepSeek Harness LLM seam, with a web settings page for browsing the ACP registry and managing configured servers

models-usage20
Updated 9/4/2026
v0.3.10
dsh-router-codebuddy

Router Codebuddy

DSH plugin: CodeBuddy supplier for dsh-router. Provides the codebuddy supplier (OAuth login, OpenAI-compatible chat gateway) to dsh-router through the router.suppliers cordis service.

models-usage20
Updated 9/4/2026
v0.1.6
dsh-agy-safe

Agy Safe

dsh plugin: use a logged-in Antigravity CLI (agy) headless session as the chat and subagent model provider

models-usage20
Updated 9/4/2026