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 & Media922Search & Research1.2kSecurity & Access1.8kModels & Usage2.5kProductivity & Workflow3.7k

All plugins

2469 plugins
v1.4.0
dsh-whale-commands

Whale Commands

Slash commands for the DeepSeek Harness Weixin channel: persona toggle & multi-persona library, session history (soft load or real session switch), model selection, token usage and balance, scheduled daily greetings. Host-side execution, zero model tokens, hot-reload. Also ships compatibility notes

↓ 0★ 2
Updated 10/29/2026
Mv2.3.0
dsh-model-auto-enricher

Model Auto Enricher

DSH Model Completion Assistant: eliminates the tedious process of manually opening dozens of models one by one after adding a new model channel in DSH to adjust context windows, enable multimodal image input, and configure reasoning effort tiers (low/high/max). Supports automatic completion upon sav

↓ 0★ 2
Updated 10/29/2026
Mv0.4.9
dsh-model-picker-control

Model Picker Control

Model picker control for DSH: rename, regroup, sort, hide and badge models across providers, with cross-provider partitions, plus suffix capsules.

↓ 0★ 2
Updated 10/29/2026
v0.1.8
codex-subscription-oauth-plugin

Codex Subscription Oauth Plugin

Out-of-tree DSH bundle for ChatGPT Codex OAuth and live models

↓ 0★ 2
Updated 10/28/2026
Qv1.4.0
@local/dsh-quota

Quota

DeepSeek Harness status bar multi-provider quota monitoring plugin: 智谱 GLM, OpenCode Go, Kimi, 小米 Token plans, DeepSeek official (balance + usage estimates), with today/7-day/30-day Token usage statistics.

↓ 0★ 2
Updated 10/28/2026
Hv0.2.0-rc.9
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

↓ 0★ 2
Updated 10/28/2026
Qv0.1.37
@iasiv5/dsh-quota-watch

Quota Watch

DSH Web sidebar monitor for GLM Coding Plan quotas and GitHub Copilot credits

↓ 0★ 2
Updated 10/28/2026
Av1.3.1
dsh-aliyun-coupon

Aliyun Coupon

阿里云云工开物学生专属代金券余额实时查看插件（DeepSeek Harness）：零 Token 消耗、真实浏览器实时抓取账单控制台。 / Live Aliyun student coupon balance viewer for DeepSeek Harness — zero-token, real-time console scrape.

↓ 0★ 2
Updated 10/27/2026
Ev1.9.0
dsh-echelon

Echelon

Echelon for DeepSeek Harness: name a few tiers, and each one becomes an ordered chain of real models with retries, failover, reasoning-level translation, context-window routing and vision routing. 挡位式模型路由：按命名选模型，失败自动降级。

↓ 0★ 2
Updated 10/27/2026
Pv0.1.7
dsh-pet-astra-yao

Pet Astra Yao

Astra Yao — a Codex v2 sprite-atlas desktop pet for DeepSeek Harness, with session-state animation, a status bubble and a DeepSeek balance readout

↓ 0★ 2
Updated 10/27/2026
Fv0.5.1
dsh-freetoken

Freetoken

Unofficial DSH plugin: deepseek-web provider bridge for development use (disabled by default).

↓ 0★ 2
Updated 10/26/2026
Gv1.4.0
@local/dsh-grok-xai

Grok Xai

Sign in to xAI with a SuperGrok or X Premium subscription and use Grok models in DeepSeek Harness.

↓ 0★ 2
Updated 10/26/2026
Av1.0.0
dsh-agent-model-router

Agent Model Router

Freely select from all models registered in DeepSeek Harness for seven roles—exploration, verification, implementation, testing, review, image recognition, and documentation—and orchestrate them in stages; share mappings across workspaces, retain separate mappings for new and old sessions, and hand

↓ 0★ 2
Updated 10/26/2026
Cv1.0.0
dsh-cyrene-balance

Cyrene Balance

Check DeepSeek API balance and today’s spending in DeepSeek Harness, with daily quota limits, over-limit alerts, and quota-only or balance-only views.

↓ 0★ 2
Updated 10/25/2026
Av0.4.0
dsh-antigravity-direct

Antigravity Direct

DeepSeek Harness (DSH) plugin: Direct proxy and model service for Google Antigravity, supporting OpenAI-compatible protocol conversion, automatic discovery and one-click synchronization of the latest model list, real-time dual model pool quota monitoring, hot-swappable network proxies, and long-text

↓ 0★ 2
Updated 10/23/2026
Rv0.9.1
dsh-reasoning-level

Reasoning Level

DeepSeek Harness unified reasoning-level plugin: one llm-reasoning setting dynamically configures the default reasoning level (thinking level) for all DSH models—automatically adds reasoning capabilities to manually declared models, sets a default level by route (only when supported by all models),

↓ 0★ 2
Updated 10/22/2026
Tv0.1.1
token-contribution

Token Contribution

GitHub-style token usage contribution calendar and analytics for DeepSeek Harness

↓ 0★ 2
Updated 10/21/2026
Iv0.1.7
@xiciyang/inference-serving

Inference Serving

Deploy a model checkpoint as a reachable inference endpoint: probe environment, select backend, migrate if needed, deploy, health-check, register the endpoint, auto-degrade on failure, roll back, tear down — fully audited.

↓ 0
Updated 10/20/2026
Pv2.0.1
dsh-plugin-peak-pricing

Plugin Peak Pricing

DeepSeek Peak/Off-Peak Pricing Period Badge (Web & Desktop): Displays the current peak/off-peak period and countdown to the next switch below the Settings button in the sidebar; when the sidebar is collapsed, hover over the dot to view details in a pop-up.

↓ 0★ 2
Updated 10/20/2026
Cv0.1.0
dsh-connect-hub

Connect Hub

DeepSeek Harness plugin: Connect models from Qoder, WorkBuddy, and Trae, providing a unified catalog, quota management, daily check-in, model toggles, and settings interface.

↓ 0★ 2
Updated 10/19/2026
v0.1.3
inference-serving

Inference Servingalt · xiciyang

Deploy a model checkpoint as a reachable inference endpoint: probe environment, select backend, migrate if needed, deploy, health-check, register the endpoint, auto-degrade on failure, roll back, tear down — fully audited.

↓ 0
Updated 10/19/2026
Mv0.2.2
dsh-model-settings

Model Settings

Model settings panel: Configure the models and reasoning intensity for the main model, sub-agents, and goal turns in one place. Changes take effect immediately upon saving (compatible with the latest dsh 0.2.1-rc.2 / DSH NEXT, with backward compatibility for 0.1.x).

↓ 0★ 2
Updated 10/19/2026
Cv0.3.0
dsh-cliproxyapi-provider

Cliproxyapi Provider

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

↓ 0★ 2
Updated 10/19/2026
Rv0.3.14
dsh-roundtable-harness

Roundtable Harness

Multi-model roundtable debate plugin: lets multiple AIs configured in DSH, each with its own persona, engage in multiple rounds of heated debate on the same topic while sharing context. The judge assigns weighted scores across six dimensions (aggressiveness/logic/persona fidelity/entertainment value

↓ 0★ 2
Updated 10/18/2026
Av0.1.0
dsh-autofill-model-metadata

Autofill Model Metadata

DSH plugin: fill custom-provider model metadata from models.dev through an explicit, pre-declared mapping - no guessing, fail-closed.

↓ 0★ 2
Updated 10/18/2026
Tv0.2.0
dsh-tool-cost-hint

Tool Cost Hint

Doesn't tell you how much you spent, only how much each tool added to your context.

↓ 0★ 2
Updated 10/18/2026
Cv1.1.2
dsh-codex-model-effort-selector

Codex Model Effort Selector

Codex desktop style model + reasoning-effort selector for DeepSeek Harness: one trigger, one popover, a model list pane and a pixel-replica effort slider.

↓ 0★ 2
Updated 10/17/2026
Tv0.2.0
dsh-token-data

Token Data

Token usage dashboard, provider balances, and subscription quotas for the dsh web GUI

↓ 0★ 2
Updated 10/17/2026
v0.8.2
@alanzhao/dsh-balance-monitor

Balance Monitor

Channel-aware balance/usage card for DeepSeek Harness: DeepSeek official balance + spend windows, Volcano Ark Agent Plan quota bars.

↓ 0★ 2
Updated 10/17/2026
Cv0.2.0
dsh-continue-on-limit

Continue On Limit

Auto-continue for the DeepSeek Harness Web GUI (harness 0.2.0): when a small local model hits its output-token cap at the tail of a session, a host-side session projection publishes the notice and the plugin automatically sends a short "continue" message so the reply keeps flowing without a manual c

↓ 0★ 2
Updated 10/17/2026
← Previous1…2526272829…83Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in