model-routing

🌊 月汐（kimi-tide）— DSH 的「每一步自动选模型」插件：贴图自动走能看图的模型，写代码走编码模型，闲聊翻译走便宜模型，每次选了谁、为什么，面板看得见 · The per-step model router for DeepSeek Harness: any connected model, routed by your rules

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unified subagent routing and evolution: prefercmd/memory serve as knowledge allow/deny lists, saving tokens.

Vision + smart model routing for DeepSeek Harness. Gemini sees. DeepSeek codes.

Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent profiles, exact model routes, declarative teams and strategies, and bounded subagent delegation - a TypeScript plugin that adds no second runtime.

TypeScript library for building multimedia-generation agents: text-to-image, video, speech and audio pipelines with capability-based model routing, automatic cross-model fallback, and BYOK direct provider calls (no gateway). 27 built-in patterns, provider-SDK-free core.

dsh plugin: DeepSeek Harness 的模型层 = raincode(模型池/缓存/重试) + /skills 浏览

Evidence-first model control plane for DeepSeek Harness

Capability-aware reasoning controls and Fast model routing for DeepSeek Harness

DeepSeek Harness 子代理模型路由插件：subagent_model 工具 + model:"auto" 路由策略（任务档位/失败升级/可审计），子代理不再继承父模型。Model-routed subagent delegation for DeepSeek Harness.

Reusable Markdown prompt profiles for DeepSeek Harness with per-turn model selection, argument substitution, and state restoration. DeepSeek Harness 可复用 Markdown Prompt Profile，支持单轮模型选择、参数替换和状态恢复。

oh-my-dsh — tiered model routing plugin for DeepSeek Harness: think/build tiers, vision delegation, image generation. MIT.

该仓库暂未提供项目说明。

Multi-model governance, routing, fallback, quota, and usage for DeepSeek Harness

Shadow-mode SLM router for DeepSeek Harness: per-turn weak/strong prediction via vertical-small-model CLI, writes shadow JSONL log

Configurable Auto model routing tier for DeepSeek Harness

为 DeepSeek Harness 提供基于关键词和语义分类的动态模型路由插件，可按任务自动选择模型与推理强度。

A token-efficient model-routing flywheel for the DeepSeek Harness.

Automatic model routing for DeepSeek Harness: three difficulty tiers (hard/normal/easy) plus vision routing, picking models you already configured under Settings ? Models. ???? + ?????????

DeepSeek Harness plugin: role-based model routing — planner (root agent) on deepseek-v4-pro, delegated executor subagents on deepseek-v4-flash; ships a prompt section and a pro-flash-routing skill.

Tiered model routing plugin for DeepSeek Harness (DSH): route delegated work to fast/medium/heavy model tiers with DoD verification, cross-provider fallback, background delegation, and per-conversation budget modes.

DSH plugin: virtual model ids backed by pluggable routing algorithms (priority, round-robin) over real provider candidates, with transparent failover.