Plugins

A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 67 models from one wallet. No accounts, no API keys.

kimi-tide（月汐）— preset-and-rule model router for DeepSeek Harness（预设+规则驱动的逐步模型路由）：named presets with ordered image/keyword-group rules route each agent step across ANY mounted provider/model (candidate pool = full host catalog enumeration, no whitelist), w

Per-step model router: named presets with ordered image/keyword-group rules route each agent step across every mounted provider and model, adding collaboration flows for image transcription, an image guard, a multi-plan quota panel, and per-step decision observability.

Connects 36 model sources (free and pay-as-you-go APIs, Codex and Kimi subscriptions, local Ollama and LM Studio) to dsh and gives other tools one authenticated OpenAI-compatible address and key. The free pool model free/auto combines free API quotas such as ModelScope, Zhipu Flash, Gemini and Cloudflare Workers AI, moves to the next provider when one is used up, and by default only uses quotas that do not charge. Models appear in dsh grouped by source; Cherry Studio, Cline and scripts can use the same address (HTTPS is set up automatically next to dsh-vps). Daily check-in for 10 services (Trae, Qoder, WorkBuddy, Doubao, MiniMax Code, WPS Lingxi, DuMate, AStudio, Huawei CodeArts, OfficeAce) with several accounts each, pasted credentials for checking in on a server, and custom check-in services described as JSON. Installed from the plugin market it sets itself up, and the engine ships as an npm package, so no GitHub access is needed.

Picks each subagent model from the local catalog by task category, unless the caller already named one. Free and quota tiers are ranked together by per-model capability tags; a pricier model is used only when no cheap model is tagged as good at that kind of work. Only providers whose remaining balance is readable, or that are account-backed, enter the candidate pool; the rest stay listed but are not routed. A panel adds per-model manual priority above the automatic order plus allow/revoke controls.

Picks each subagent model from the local catalog by task category, unless the caller already named one. Free and quota tiers are ranked together by per-model capability tags; a pricier model is used only when no cheap model is tagged as good at that kind of work. Only providers whose remaining balance is readable, or that are account-backed, enter the candidate pool; the rest stay listed but are not routed. A panel adds per-model manual priority above the automatic order plus allow/revoke controls.

OpenAI-compatible gateway for every connected model: groups with failover, aliases, session stickiness, usage charts, API keys and a LAN listener (open to the whole network until you create an API key).

Two-level model routing: pick the best model group first, then the best channel within that model; a failure switches channel before switching model. Preference mode pins one model across its channels, a status bar under the composer shows the live model, channel health and the day's token usage, and a speed/intelligence report can be imported as the routing prior. Exposes a model_orchestrator tool and a /route command.

FreeDSH — free-first multi-model routing, safe core updates and pt-BR/Windows support for DeepSeek Harness. Installable as a DSH bundle (dsh plugin add). Unofficial project.

Two-tier model router for DeepSeek Harness — LLM-Judge routing, multi-model fallback chains, exponential-backoff failover, and task-level orchestration (DSH adaptation of pi-shift-router)

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。