CATEGORY
Models & Usage DSH plugins
Verified manifests and exact versions in this category.
All plugins
876 pluginsdsh-router-coreRouter Core
DSH plugin: a simplified 9router (AI routing gateway). Adds a 路由系统 (Routing System) sidebar entry beside 记忆系统; the panel shows suppliers, account pool, combos, and endpoint/API keys.
dsh-client-ui-cpa-quotaClient Ui Cpa Quota
CliProxyAPI quota indicator: a native-styled ring left of the composer model name; hover shows per-account provider quotas, subscription plans, and status for Codex, Claude, Antigravity, Gemini CLI, Kimi, xAI/Grok, and other CPA auth providers. Targets the current dsh plugin contract (settings-names
dsh-cache-billingCache Billing
Cache Billing: Real-time billing in the context ring overlay—with separate details for the current step, current round, and session total; tokens and costs shown for cache hits, cache misses, and output; automatic peak/off-peak pricing; third-party relay usage is billed as usual. Addresses the issue
dsh-model-pickerModel Picker
DSH Web UI model selector replacement plugin: dialog-style model selection (fuzzy search / collapsible provider groups / favorites / thinking level dropdown), reusing @deepseek-ai/dsh-client-ui-primitives.
dsh-usage-monitorUsage Monitor
Session-log usage dashboard for DeepSeek Harness
dsh-whale-widget-bowlWhale Widget Bowl
DeepSeek balance whale widget in the bottom-right corner of the DSH Web interface · Iron Basin Whale Girl Edition (includes three appearance options—default, bowl-balancing, and bowl-holding—steel pipe sound effects, today’s usage, peak/off-peak pricing, random lines, and per-round usage statistics)
@dsh-polyglot/bundleBundle
dsh-polyglot — the model switch for DSH: one generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek provider presets, and automatic provider fallback when a free tier rate-limits you
dsh-plugin-rollout-scoutPlugin Rollout Scout
Detect which conversation model your DeepSeek Harness account is served: score probe conversations' live chain-of-thought, cancel old-model probes in seconds, keep confident catches.
dsh-proactiveProactive
Autonomous intelligent multi-model collaborative scheduling system — proactive perception, autonomous decision-making, multi-model parallelism, quality reflection and self-healing, experience accumulation and evolution
@1lyn-en/dsh-whaleWhale
Whale doesn't waste words—accomplish more with fewer words in DSH's minimalist language mode, saving 60–75% of output tokens
@deepseek-ai/dsh-llm-pi-ai-antigravityLlm Pi Ai Antigravity
Google Anti Gravity and Cloud Code Assist Coding Plan LLM Provider plugin for DeepSeek Harness
dsh-opencode-go-monitorOpencode Go Monitor
Money-saving + balance monitoring floating window (DSH Web UI plugin): DeepSeek balance/official website usage/currency units/low-price analysis/high-price zone hourly limits/breakpoint truncation/low-usage compression/voice alerts
dsh-musageMusage
Coding-plan quota and balance readout for the DSH composer toolbar: MiniMax, DeepSeek, Kimi, OpenRouter and Zhipu windows follow the selected model; API keys are reused from DSH model settings.
@xmoon76/dsh-subagent-routerSubagent Router
DSH model-facing delegation tool that routes continuable/one-shot subagents to a model-selected LLM provider and model
dsh-token-petToken Pet
Cute usage widget Token 泡泡 (Token Pet): a 「布布」doll in the top-right corner of the conversation header, displaying real-time context usage, session totals, and context breakdown, along with the date and day of the week, current weather, a 3-day forecast, and extreme weather alerts. Follows the theme
dsh-legionLegion
DeepSeek Harness (DSH) plugin for multi-agent orchestration: semantic agent Profiles, exact LLM model routing, declarative Teams and Strategies, and bounded subagent delegation.
@aaravarr/dsh-subagent-maxSubagent Max
Subagent delegation with per-call model/provider override (host) + multi-panel live streaming subagent viewer (client)
dsh-connect-workbuddyConnect Workbuddy
Connect locally signed-in WorkBuddy models to DeepSeek Harness with a read-only credits overview and model management.
dsh-pseudo-visionPseudo Vision
Adds opt-in image-capable sibling routes for text-only providers and converts image blocks into budgeted, locally enhanced OCR, color-statistics, pixel-scan, and metadata evidence before delegation.
dsh-agent-routerAgent Router
DeepSeek Harness multi-model routing plugin: route tasks to custom specialist agents (vision / image generation / translation / speech / subagent) with per-agent providers & models, multimodal account sign-in, OAuth account pools, and realtime usage stats
dsh-liangwenguLiangwengu
Liangwengu Reminder: alerts based on DeepSeek API peak and off-peak pricing periods (Beijing Time)—“run fast” before the peak and “open the valley” when the peak ends. Cartoon pop-up in the lower-right corner + browser system notifications + alert sounds.
dsh-opencode-go-autosyncOpencode Go Autosync
Sync opencode-go models from https://models.opencode.ai/api.json into llm-pi-ai provider opencode-go-autosync (one-click create/update in settings).
dsh-llm-opencode-goLlm Opencode Go
OpenCode Go models, mixed Completions/Responses/Messages chat, and subscription usage for DeepSeek Harness
dsh-llm-ollamaLlm Ollama
Ollama Cloud models, OpenAI-compatible chat, and Web Search/Fetch for DeepSeek Harness
dsh-usage-ledgerUsage Ledger
DSH token usage & cost ledger: per-session aggregation, official multi-vendor pricing (peak/off-peak aware), budget control, cost-intelligence insights (projections, anomaly detection, health score, attribution), Prometheus metrics, SSE dashboard
@zhangyi/dsh-llm-ollamaLlm Ollamaalt · @zhangyi
Ollama native protocol (/api/chat) provider for DeepSeek Harness: llm-ollama settings namespace, serving LlmAdapter, /api/tags model discovery, and a whole-page Ollama settings section.
dsh-cost-estimateCost Estimate
DSH plugin: before answering a large question, show an estimate of tokens and DeepSeek API cost as an inline row in the Web chat stream, then update it with the actual usage after the answer.
dsh-model-gardenModel Garden
A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, live per-task cost, prices and context windows.
dsh-route-resilienceRoute Resilience
Multi-route high availability, fault isolation and observability for DeepSeek Harness. Route groups fail over between authorized provider routes on rate limits (429 / Retry-After), transport errors and auth/quota failures, with per-route quarantine (exponential backoff) and disablement.
@alanzhao/dsh-balance-monitorBalance Monitor
Channel-aware balance/usage card for DeepSeek Harness: DeepSeek official balance + spend windows, Volcano Ark Agent Plan quota bars.