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 & Media916Search & Research1.2kSecurity & Access1.8kModels & Usage2.5kProductivity & Workflow3.6k

All plugins

2459 plugins
Dv0.1.0-rc.11
dsh-deepseek-billing

Deepseek Billing

DSH WebUI plugin: Display DeepSeek account balance in the sidebar and estimate costs by session

↓ 0★ 0
Updated 9/22/2026
Lv0.1.0
dsh-llm-router

Llm Router

Task-aware automatic model router (auto route) for the DeepSeek Harness: picks a backend model per request (vision / long-context / default) and falls back across configured models on clean pre-content failures.

↓ 0★ 0
Updated 9/21/2026
Rv0.1.0
dsh-reasoning-effort-inject

Reasoning Effort Inject

Frontend-injected per-model reasoning-effort (thinking strength) configuration for custom pi-ai providers. Registers a per-model 思考强度 editor into the Settings -> Models provider card and persists reasoningEfforts through the settings Remote.

↓ 0★ 0
Updated 9/21/2026
Jv0.1.0
dsh-jev-adapter

Jev Adapter

Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. Registers a jev_decide tool on DeepSeek Harness (dsh).

↓ 0★ 0
Updated 9/21/2026
Mv0.3.1
dsh-model-usage

Model Usage

DeepSeek Harness plugin: shows model usage and account balance in the session header — OpenCode Go plan usage (rolling / weekly / monthly) with the selected model's monthly cap, and DeepSeek account balance — each only while a matching model is the active selection.

↓ 0
Updated 9/21/2026
Pv0.1.2
@knyazevai/dsh-provider

Provider

DeepSeek Harness provider bundle for the KnyazevAI API

↓ 0★ 0
Updated 9/21/2026
Dv0.2.0
dsh-deepseek-balance-badge

Deepseek Balance Badge

DeepSeek account balance badge in the DSH sidebar footer, with a settings card for the refresh period. The API key stays in the host process.

↓ 0★ 0
Updated 9/21/2026
Fv0.1.0
dsh-failover-continue

Failover Continue

Unified auto-continue + model failover for DeepSeek Harness: ordered fallback chain with circuit breaking plus automatic continuation of failed turns, one bilingual (RU/EN) settings card.

↓ 0★ 0
Updated 9/21/2026
Pv1.1.0
dsh-peak-usage

Peak Usage

DeepSeek Harness plugin: displays the current session's spending in real time below the input box, calculates the cost of each request according to the official peak/off-peak time-based pricing, and reads the account balance

↓ 0★ 0
Updated 9/21/2026
Pv0.2.0
dsh-plugin-glm-balance

Plugin Glm Balance

DSH web plugin: GLM (bigmodel.cn) quota balance indicator beside the composer context meter, shown when the current provider is zai-coding-cn; token, provider id, and auto-refresh interval configurable in its own settings section.

↓ 0★ 0
Updated 9/21/2026
Ov0.1.4
dsh-openai-account-connector

Openai Account Connector

Community OpenAI account model connector for DeepSeek Harness

↓ 0★ 0
Updated 9/21/2026
Qv0.5.0
dsh-qoder-cli

Qoder Cli

Reuse the Qoder desktop app's sign-in or run the Qoder device login from the card to bring Qoder's models into DeepSeek Harness — 10 live-verified model keys over the Qoder model gateway, with an expandable settings card in the Web UI.

↓ 0★ 0
Updated 9/21/2026
Tv1.8.0
dsh-token-feiyong

Token Feiyong

DSH（DeepSeek Harness）token billing plugin: includes official pricing tables (DeepSeek distinguishes peak and off-peak rates; 智谱 GLM is calculated separately), calculates costs per request (cache hits / misses / output), and provides account balance, per-request, and current-conversation statistics;

↓ 0★ 0
Updated 9/20/2026
Lv1.0.1
dsh-llama-model-manager

Llama Model Manager

DSH plugin: manages the Windows llama-server.exe model lifecycle (start / stop / switch / recover) behind a stable OpenAI-compatible gateway, with graceful Ctrl+C shutdown that actually frees VRAM.

↓ 0★ 0
Updated 9/20/2026
Tv1.0.5
dsh-token-ledger

Token Ledger

Token ledger: monitor DSH's daily token consumption by local date (uncached input/cached reads/output), with a settings page card, input box badge, /tokens command, and token_usage model tool.

↓ 0★ 0
Updated 9/20/2026
v0.2.1
dsh-plugin-ai-gateway

Plugin Ai Gateway

DeepSeek Harness plugin: Visual console for an AI aggregation gateway, integrating Google Antigravity and OpenAI Codex reverse proxies, a multi-account rotation pool, 5h/weekly quota dashboards, and failover.

↓ 0★ 0
Updated 9/20/2026
Uv0.1.0
@dsh-external/ui-usage-stats

Ui Usage Stats

Settings page for workspace/session/period/model token usage and DeepSeek cost

↓ 0★ 0
Updated 9/20/2026
Nv0.1.1
@libre-webui/dsh-native-provider

Native Provider

Use DeepSeek Harness providers in Libre WebUI over a private local connection.

↓ 0★ 0
Updated 9/19/2026
v0.2.0
dsh-opencode-go-dashboard

Opencode Go Dashboard

OpenCode Go & Google Antigravity (Gemini) intelligent dual-engine usage monitoring panel: supports adaptive source switching by model/provider, dynamic OAuth quota refresh, and a quick progress ring in the conversation bottom bar

↓ 0★ 0
Updated 9/19/2026
Mv0.4.0
dsh-model-switcher

Model Switcher

Visual custom-provider presets and model switching for DeepSeek Harness Web.

↓ 0★ 0
Updated 9/19/2026
Av1.3.0
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

↓ 0★ 0
Updated 9/19/2026
Hv0.1.0
dsh-hunyuan-3d

Hunyuan 3d

Tencent Cloud Hunyuan 3D (混元生3D / ai3d OpenAPI) modeling tools for dsh: text-to-3D and image-to-3D job submission with result polling and on-disk asset download.

↓ 0★ 0
Updated 9/18/2026
Sv0.3.0
dsh-ssh-remote-tunnel

Ssh Remote Tunnel

DSH plugin: automatic SSH port-forward tunnel to a remote LLM/vLLM server (ping gate, any SSH client - OpenSSH ssh or PuTTY plink - with automatic password, health monitor) plus provider registration for subagent model selection. No plink required: OpenSSH ssh with password (SSH_ASKPASS/sshpass) or

↓ 0★ 0
Updated 9/18/2026
Mv0.1.1
dsh-model-relay

Model Relay

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

↓ 0★ 0
Updated 9/18/2026
Wv0.1.0
dsh-werewolf

Werewolf

狼人杀 (Werewolf) round-table plugin for the DeepSeek Harness Web GUI: 8 customizable AI seats, per-seat provider routing, live reasoning captions, browser speech, and token betting.

↓ 0★ 0
Updated 9/17/2026
v0.1.1
dsh-session-usage

Session Usage

Session usage view: tokens, wall time and cache share per model and per turn, as a conversation view.

↓ 0★ 0
Updated 9/17/2026
v0.2.0
dsh-token-hud

Token Hud

Global real-time Token HUD for DeepSeek Harness Web: draggable floating window showing live output tok/s, cumulative tokens, and per-session running/retrying status across all DSH sessions.

↓ 0★ 0
Updated 9/17/2026
Ov0.3.0
dsh-offpeak-job

Offpeak Job

Session off-peak toggle + multiple provider-configured off-peak windows

↓ 0★ 0
Updated 9/17/2026
Mv0.2.0
@jxiansen/dsh-model-switcher

Model Switcheralt · @jxiansen

DSH Model Switcher — searchable palette that overwrites the composer model seat (Cmd+K).

↓ 0★ 0
Updated 9/17/2026
Tv3.0.0
dsh-thinking-levels-settings

Thinking Levels Settings

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

↓ 0★ 0
Updated 9/17/2026
← Previous1…7172737475…82Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in