CATEGORY
Verified manifests and exact versions in this category.
@deepseek-ai/dsh-model-catalog-bigmodel
Zhipu AI BigModel and GLM Coding Plan LLM Provider model catalog plugin for DeepSeek Harness
dsh-cost-insights
Auditable usage, cost, token, cache, balance and pricing analytics for DeepSeek Harness.
dsh-opencodego-quota
OpenCode Go (opencode.ai/zen/go) quota usage plugin: keeps a quota card permanently in the DSH Web GUI left sidebar, displaying usage progress bars, converted amounts, reset times, and refresh times for three windows: daily (past 5 hours), weekly, and monthly; the automatic refresh interval can be f
@abcdefu_cja/dsh-usage-stats
DSH API usage statistics: tokens, requests, rounds, cache hits, cost estimates, and balances/quotas for multiple providers.
dsh-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 settings-page management panel.
dsh-mornye-quota-pet
DSH 莫宁 quota desktop pet: Real-time display of the three OpenCode Go plan quotas (monthly/weekly/rolling), desktop-pet interactions (dragging/snapping/mirroring/bouncy animation/menu/dialogue/sound effects), persistent startup
dsh-offpeak-saver
DeepSeek Harness Off-Peak Cost-Saving Scheduler: schedules non-urgent tasks for idle periods and automatically quantifies the savings.
dsh-workspace-hub
DSH workspace folders: categorize workspaces into folders in the left sidebar (drag reorder for folders/workspaces/sessions, inline edit, one-click expand/collapse, search) plus per-workspace token usage and cost stats (inline totals, hover detail card, overview panel with per-model price cards; Dee
dsh-economizer
Save tokens on the DeepSeek Harness (dsh) — on-demand tools / MCP / skills loading, cache-stable, with a v3 retrieval matcher. Works as an agent preset (picker-selected 「省钱模式」) or as a dsh.bundle (global, installable via `dsh plugin add`).
dsh-quota-dashboard
dsh-cost-meter 的 fork:会话费用/Token 缓存统计 + 统一额度看板(DeepSeek 余额 / OpenCode GO / Kimi For Coding / GLM Coding Plan / 火山方舟)。Fork of dsh-cost-meter with a unified multi-provider quota dashboard.
@dsh-external/dsh-cost-guard
成本守卫: A cost-saving plugin for DeepSeek V4-Flash-0731 pure API pricing—calculates session costs, cache hit rates, and the amount saved with full cache hits according to the official peak/off-peak tiers dated 2026-08-17 (peak: 09:00-12:00 / 14:00-18:00); ¥ budget guard (budget = hard limit: once the
dsh-llm-web-bridge
DSH web plugin: bridge to third-party web LLMs (Gemini, ChatGPT, Doubao, custom) — agent-driven consult_llm tool with review/code-review/adversary/verify roles, text-log primary UI with on-demand live view, named sessions, token metering, headed/headless browser daemon.
@deepseek-ai/dsh-plugin-usage
Usage (用量) deployment plugin for DeepSeek Harness (DSH): a real-time token & cost dashboard tab next to chat/trajectory, with live streaming estimates, DeepSeek official peak/off-peak pricing and OpenCode Go plan pricing, custom price table, and CSV/JSON export.
dsh-llm-longcat
LongCat (LongCat-2.0) adapter for the DeepSeek Harness LLM seam — 1M context, thinking mode, tool calling
@adverts13/dsh-auto-model-router
Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.
dsh-llm-governor
Multi-model governance, routing, fallback, quota, and usage for DeepSeek Harness
dsh-llm-autorouter
AutoRouter (model routing gateway / relay) LLM adapter for the DeepSeek Harness
dsh-feiyu-wardrobe
Big Fat Fish Wardrobe — DSH plugin: token spending becomes fish food, with a built-in “Dressing Room” dress-up mini-game in the sidebar (raising-a-daughter style, conservative content: custom WebGL2 2.5D animated characters with 65-bone rigging/skinning, hair and skirt physics, blinking and lip-sync
dsh-trae2api
DeepSeek Harness plugin: use Trae enterprise models with just a Personal Access Token (direct llm_raw_chat, no trae2api/traecli).
dsh-connect-teleagent
Connect the locally signed-in TeleAgent (China Telecom AI Xingchen Super Agent desktop client) model to DeepSeek Harness: native kernel traffic + true streaming + multi-turn + images + tool calls + chain of thought + credits.
@breey05/dsh-balance-widget
Provider-aware API balance and observed spend that follow the selected Harness model.
dsh-team-model
Agent Teams teammate models: Allows both the model and the user to specify each teammate’s model, with switching available in the Web UI conversation header, input toolbar, and settings page.
@local/subagent-switch
DSH desktop plugin: routes every subagent to the best available local model — free-first, quota-aware, capability-matched — and adds a control panel next to the session model bar.
dsh-rustvy
Rustvy for DeepSeek Harness: vendor marks in the model picker, a model list kept in step with what the provider actually serves, a raised stream idle timeout so long-reasoning models are not cut off by the adapter's watchdog, a ClientHello-fragmenting transport that reaches model traffic when a DPI
@fractalsynapse/dsh-chapters
dsh plugin: verbatim chapter archive + zero-token index for small-context models
dsh-model-navigator
Replace the official general model selector with global search, favorites, recently used, family navigation, and thinking intensity, reusing the official session model state
@zdt3476/dsh-subagent-routes
A routing table that assigns providers, models, and thinking levels to sub-agents by workspace directory, then injects them into sub-agent AgentOptions after longest-prefix matching.
whale-purse
Whale Wallet: Adds balance, spending, and peak/low alerts to the whale-girl desktop pet (summoned via the menu button, with spending displayed at each step)
dsh-minimax-connect
Use the MiniMax Code (Mavis) subscription already signed in on this machine as a DSH model provider, with self-renewing credentials, thinking-effort mapping, a points panel, subscription-quota panel and daily check-in.
dsh-2d-model-picker
A 2D model picker for DeepSeek Harness — select a model and reasoning effort in one drag.
