DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

Plugins Presets Docs News

Community

Publish a plugin Contact Report an issue

Resources

Plugin Hub on GitHub DeepSeek Harness System status Privacy 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 plugins Agents & Orchestration1.5k Memory & Context2.1k Coding & Developer Tools4k UI & Customization5.6k Integrations & Communication3k Vision & Media918 Search & Research1.2k Security & Access1.8k Models & Usage2.5k Productivity & Workflow3.6k

All plugins

2448 plugins

Peakrate

Peak / off-peak rate badges and switch countdown for DeepSeek Harness — per provider, per model, in the model selector and the composer tool row. Judges each provider by its own time zone and schedule instead of DeepSeek-only hours.

Updated 11/4/2026✓ Scan passed

@dsh-ai-providers/runtime

Runtime

DSH plugin that selects and exposes embedding, reranking, decision, speech, and image providers.

↓ 596

Updated 11/4/2026✓ Scan passed

@sunshaobei/dsh-balance-panel

Balance Panel

Provider quota/balance widget for the dsh web surface: an inline sidebar card above the Settings row (collapsed glanceable row expanding into a Harness-native card with a settings panel), fed by a loopback Connection RPC channel whose host half proxies ea

Updated 11/4/2026

dsh-modeltester

Modeltester

ModelTester — model detection & attribution panel for the DeepSeek Harness web chat. Ranks vendor families (DeepSeek / Anthropic / OpenAI / Google / Qwen / GLM / Kimi / MiniMax / MiMo / Baichuan / SkyWork / LongCat / InternLM / Step / Yi / Llama / Mistral

Updated 11/4/2026

dsh-llm-discovery

Llm Discovery

Endpoint model discovery, the models.dev catalog service, and the primitives the discovery plugins share

Updated 11/4/2026

dsh-opencode-go-usage

Opencode Go Usage

DSH (DeepSeek Harness) plugin: OpenCode GO plan quota widget in the sidebar, same-origin usage proxy, and a /opencode-go chat command

Updated 11/4/2026✓ Scan passed

@young1lin/dsh-glm-quota

Glm Quota

DSH plugin: Zhipu/GLM Coding Plan quota — host fetch/cache/backoff plus a compact sidebar status and on-demand quota popover

Updated 11/4/2026✓ Scan passed

@choi-p/dsh-deepseek-balance

Deepseek Balance

DeepSeek account balance in the dsh web sidebar footer, configured from a settings section on the plugin's own page in Settings → Plugins.

Updated 11/4/2026✓ Scan passed

dsh-whale-post-gate

Whale Post Gate

配额与计费闸＋回环闸（示例②的挂点） · Quota and billing gate + loop gate (example (2)'s socket)

Updated 11/4/2026✓ Scan passed

Sseye

The LLM debug console inside DeepSeek Harness — capture every model call, see everything, replay anything.

Updated 11/4/2026✓ Scan passed

@floatingdeaming/minimax-usage

Minimax Usage

DSH bundle plugin: provides ctx.minimaxUsage service, registers minimax.getUsage / minimax.hasApiKey JSON-RPC handlers, and ships a browser client that renders the 「用量」 section in Settings (one `dsh plugin add` installs everything).

Updated 11/4/2026✓ Scan passed

@deepseekstudio/dsh-deepseek-pet

Deepseek Pet

DeepSeek 桌宠: Connect “DSH account balance + 蓝鲸女仆桌宠.” The host queries the balance, sends it to the desktop floating window through the 127.0.0.1 loopback interface, and provides the two model tools pet_balance / pet_control.

Updated 11/4/2026

@shawnkung/dsh-balance-monitor

Balance Monitor

DSH Web sidebar balance and usage monitoring plugin, supporting DeepSeek, Kimi, 智谱 GLM, and TeamoRouter.

Updated 11/4/2026✓ Scan passed

@dsh-enhanced/traex-acp-provider

Traex Acp Provider

Use a local TraeX coding agent as a DeepSeek Harness model provider over ACP.

Updated 11/4/2026

dsh-model-rotator

Model Rotator

Model auto-ranking and transparent failover for DeepSeek Harness: ranks discovered models by measured connectivity and speed, switches to the next candidate inside the same turn when the current one is unusable, and ships a grouped model list with per-cha

Updated 11/4/2026

dsh-gemini-multimodal

Gemini Multimodal

DeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.

Updated 11/4/2026✓ Scan passed

dsh-codebuddy-sdk

Codebuddy Sdk

DeepSeek Harness plugin: CodeBuddy (Tencent Agent SDK) as an LLM provider (ctx.llm).

Updated 11/4/2026

@badai147/dsh-ocgo-usage

Ocgo Usage

OpenCode Go usage stats for the DeepSeek Harness Web GUI: compact bottom-left sidebar button with a hover detail card

Updated 11/4/2026✓ Scan passed

dsh-go-balance

Go Balance

OpenCode Go subscription balance widget for DeepSeek Harness Web: rolling/weekly/monthly quota remaining, shown at the right end of the composer tool row.

Updated 11/4/2026✓ Scan passed

dsh-llm-friendli

Llm Friendli

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support

Updated 9/15/2026✓ Scan passed

dsh-gemini-tool-schema

Gemini Tool Schema

DeepSeek Harness plugin — normalize tool schemas into the strict OpenAPI 3.0 subset that Gemini function declarations accept (fixes HTTP 400 on MCP and built-in tools).

Updated 11/4/2026✓ Scan passed

dsh-usage-heatmap

Usage Heatmap

Model usage statistics dashboard: metric cards for total Tokens/peak usage/longest session/consecutive days + GitHub-style Token heatmap (daily/weekly/cumulative toggle) + activity insights, using data aggregated from local DSH usage

Updated 11/4/2026

@welsione/dsh-model-router

Model Router

Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a set

Updated 11/4/2026

dsh-effort-slider

Effort Slider

Replaces the “Reasoning Level / Effort” dropdown in the official DSH model menu with a Codex-style continuous slider and flowing light particle effects (WebGL2). Panel colors always follow the official Harness theme, with real-time theme/change switching and no separate appearance settings. No host-

Updated 11/4/2026✓ Scan passed

dsh-tavily-pool

Tavily Pool

Tavily-backed web search and page fetching for DeepSeek Harness: multi-key pool with balance-aware scheduling, automatic failover, cooldown, and official /usage balance reporting.

Updated 11/4/2026

Loom

Loom (织机) — second-validator plugin for DeepSeek Harness: a silent external coach that weaves your agent's tools, skills, config and even its model from usage history, with deterministic verification and cold-apply.

Updated 11/4/2026

@dsh-ai-providers/openai

Openai

OpenAI language, embedding, decision, speech, and image provider for DSH.

Updated 11/4/2026✓ Scan passed

dsh-codex-provider

Codex Provider

OpenAI Codex provider for DeepSeek Harness with device-code OAuth, Codex CLI import, token refresh, and a web settings panel.

Updated 11/4/2026

dsh-plugin-local-infer

Plugin Local Infer

DeepSeek Harness plugin that manages local inference engines (llama.cpp, NInfer, Hyper-Qwen, Strata): configure, size, launch, and publish a local engine as a DSH model. Installable bundle that mounts the localInfer service, engine providers, model-facing tools, and the Web UI as one profile layer.

Updated 11/4/2026✓ Scan passed

Gpt Link

DeepSeek Harness plugin: sign in with ChatGPT to use GPT models through DSH's bundled pi-ai Codex route, and see that account's quota.

Updated 11/4/2026✓ Scan passed

← Previous 1…9 10 11 12 13…82 Next →

DeepSeek Harness Plugin Hub

Profiles Plugins Categories News Docs Sign in Manage Profiles

Profiles Plugins Categories News Docs Sign in