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.

Models & Usage DSH plugins — Page 42

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1041Memory & Context1301Coding & Developer Tools2800UI & Customization3661Integrations & Communication1911Vision & Media617Search & Research862Security & Access1266Models & Usage1684Productivity & Workflow2242

All plugins

1684 plugins
Lv0.6.0
dsh-llm-pi-ai-headers

Llm Pi Ai Headers

DeepSeek Harness LLM User-Agent/header injector with key pool round-robin: keeps the official llm-pi-ai adapter, re-injects user-agent, and supports multi-key rotation per provider. | DeepSeek Harness LLM 请求头注入器 + Key 轮询：保留官方适配器，补回 User-Agent，支持按提供商多 Key Round-Robin 轮询。

security-accessmodels-usage★ 0↓ 0
Updated 10/2/2026
Ov0.1.2
dsh-offpeak

Offpeak

DSH plugin: holds DeepSeek model calls during peak pricing hours so they are sent at off-peak rates.

models-usageproductivity-workflow★ 0↓ 0
Updated 10/2/2026
v1.2.1
@leaf233/dsh-model-gateway

Model Gateway

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.

models-usage★ 0↓ 0
Updated 10/2/2026
Wv1.1.1
@local/dsh-wallet-hud

Wallet Hud

Sidebar DeepSeek wallet balance for the Harness Web UI

models-usageui-customization★ 0↓ 0
Updated 10/2/2026
Av0.2.0
dsh-antigravity-usage

Antigravity Usage

Antigravity quota / usage monitoring: real-time quota via the local language server API; offline usage only scans the local session database (historical data can be viewed even when Antigravity is not open)

models-usage★ 0↓ 0
Updated 10/2/2026
v2.0.2
dsh-model-ultra

Model Ultra

Model Ultra — DSH plugin for llm-pi-ai provider lifecycle: create/edit, custom headers, enable/disable with uninstall-restore safety, per-model thinking effort, OpenRouter provider routing, smart routing, composites, observability, and per-model connectivity tests

models-usage★ 0↓ 0
Updated 10/2/2026
Mv0.1.0
dsh-mnn-chat

Mnn Chat

Integrate MNN Chat's custom API service with DSH: register the OpenAI-compatible HTTP service of mobile MNN Chat (MnnLlmChat) as an LLM provider in DSH, enabling direct conversations in 大龙虾

models-usage★ 0↓ 0
Updated 10/2/2026
Qv0.1.0
dsh-quilt-compact

Quilt Compact

Compaction-chain backend for the DeepSeek Harness: tiered model-pool summarization with per-model cooldown, overlapping chunking, and session-model fallback.

memory-contextmodels-usage★ 0↓ 0
Updated 10/2/2026
Cv0.1.1
dsh-compaction-policy

Compaction Policy

Put DSH's automatic context compaction trigger where you want it, per provider/model. Stops DeepSeek Harness from condensing a conversation far earlier than the configured threshold on models with smaller context windows.

memory-contextmodels-usage★ 0↓ 0
Updated 10/1/2026
Av0.3.20
@jizuo/account-plugin

Account Plugin

即作账号: Browser login, account entitlements, and quotas

security-accessmodels-usage★ 0↓ 0
Updated 10/1/2026
Sv1.0.0
dsh-sub2api-usage

Sub2api Usage

Sub2API usage panel: Displays a balance/usage summary in the DSH left sidebar. Click to view full usage details. The query interface (service URL, mode, path, and field pointers) is fully customizable.

models-usageui-customization★ 0↓ 0
Updated 10/1/2026
Mv0.2.19
dsh-model-health

Model Health

DSH plugin that lists all configured models with availability/latency testing, by reading $DSH_HOME/settings.yaml.

models-usage★ 0↓ 0
Updated 10/1/2026
Tv1.0.0
dsh-tokens-ci

Tokens Ci

tokens.ci usage dashboard for DeepSeek Harness: daily token activity, cost, token mix, model shares and leaderboard standing, as a settings page.

models-usageui-customization★ 0↓ 0
Updated 10/1/2026
Tv1.3.0
@local/token-usage

Token Usage

Token usage dashboard for the DeepSeek Harness settings panel: per-day/week/month tokens by model, pure-SVG charts, zero host changes.

models-usageui-customization★ 0↓ 0
Updated 10/1/2026
Cv0.8.2
dsh-client-ui-model-switcher

Client Ui Model Switcher

One-click provider/model switcher for the DeepSeek Harness web GUI: a session-header action that lists every configured provider and its models and switches the session in a single click.

models-usageui-customization★ 0↓ 0
Updated 10/1/2026
Dv1.0.0
dws-quota

Dws Quota

DSH plugin: shows the Deepwerkspace estimated-remaining-token count (5.5 x output-token quota) in the web client composer dock, next to the context meter. The API key is read from the credentials store (ref DEEPWERKSPACE_API_KEY) and never reaches the browser.

models-usageui-customization★ 0↓ 0
Updated 10/1/2026
Lv0.1.0
dsh-llm-ollama-native

Llm Ollama Native

DSH LLM adapter that speaks Ollama's native /api/chat instead of the OpenAI-compatible endpoint, so think:false/low/medium/high actually reaches the model.

models-usage★ 0↓ 0
Updated 10/1/2026
Pv0.1.0
dsh-plugin-session-insights

Plugin Session Insights

dsh plugin: cross-session analytics. Host accumulates per-session usage into monthly JSONL sidecars and serves /insights + CSV export; web client gains a Session Insights tab from verified projections.

models-usage★ 0↓ 0
Updated 10/1/2026
Pv0.1.0
dsh-plugin-cost-ledger

Plugin Cost Ledger

Persistent cost ledger for the DeepSeek Harness: every priced model call lands in a monthly JSONL file; /ledger renders monthly reports, /ledger-export writes CSV, and the agent can query its own spend via ledger_query.

models-usage★ 0↓ 0
Updated 10/1/2026
Pv0.1.0
dsh-plugin-relay-quota

Plugin Relay Quota

dsh plugin: read remaining quota and usage from any OpenAI-compatible relay (billing surface), via /quota and the quota_check tool.

models-usage★ 0↓ 0
Updated 10/1/2026
Av0.1.0
dsh-agent-monitor

Agent Monitor

Read-only real-time monitoring dashboard for DSH Web GUI: activity stream + four token buckets + peak/off-peak pricing costs + context usage + sub-agents + wallet balance.

models-usageagents-orchestrationui-customization★ 0↓ 0
Updated 10/1/2026
v0.1.3
dsh-llm-fidelity

Llm Fidelity

High-fidelity model calls for DeepSeek Harness: auto-adapts rejected optional parameters and keeps token usage accounting faithful

models-usage★ 0↓ 0
Updated 10/1/2026
Cv0.1.7
dsh-cache-warmer

Cache Warmer

Estimated cache time and opt-in, cost-aware prompt-cache warming for DeepSeek Harness sessions.

models-usagememory-context★ 0↓ 0
Updated 10/1/2026
Pv0.2.0
dsh-plugin-cache-guard

Plugin Cache Guard

dsh plugin: prefix-cache health guard. Separates prefix rewrites from ordinary context growth using the three disjoint usage buckets, and estimates the tokens re-billed at full price.

models-usagememory-context★ 0↓ 0
Updated 10/1/2026
Lv0.4.0
dsh-live-pricing

Live Pricing

DeepSeek Harness peak/off-peak time bar: Always displays below the input box whether it is off-peak, the current model, and this session’s cost; click to view the current real-time unit price.

models-usageui-customization★ 0↓ 0
Updated 10/1/2026
Lv0.5.3
dsh-llm-auto

Llm Auto

DSH host plugin: registers an `auto` model route that internally tries multiple “provider + model” entries in the configured order; if one fails **before producing any content**, it first retries in place within that route using the same strategy as the official implementation (transient-error allow

models-usage★ 0↓ 0
Updated 10/1/2026
v0.5.1
@viztor/dsh-opencode

Opencode

OpenCode on DeepSeek Harness — session affinity, Zen/Go gateway origin headers, and free-tier tool fallback for OpenCode models.

developer-toolsmodels-usage★ 0↓ 0
Updated 10/1/2026
Cv0.3.0
dsh-connect-qoder-x

Connect Qoder X

Integrate Qoder models into DeepSeek Harness: use a PAT to call the same model service as Qoder CLI, with support for separate domestic and international regions, model toggles, context windows, and daily check-ins, plus a read-only quota overview.

models-usage★ 0↓ 0
Updated 9/30/2026
Lv1.5.0
dsh-llm-codebuddy-power

Llm Codebuddy Power

A full-featured CodeBuddy (WorkBuddy) provider plugin.

models-usage★ 0↓ 0
Updated 9/30/2026
Tv1.1.0
dsh-token-rush

Token Rush

DSH Web GUI 会话悬浮仪表：实时 token / 消耗估算 / 账户余额，高峰时段自动变橙红色的 rush-hour 提示小窗，可拖动。A floating session HUD for the DSH Web GUI: live token spend, estimated cost and API balance, turning orange-red during DeepSeek rush hours.

models-usageui-customization★ 0↓ 0
Updated 9/30/2026
← Previous1…4041424344…57Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in