dsh-model-router：面向 DeepSeek Harness Desktop 的成本感知模型路由工作台
dsh-model-router（@ljwei-stak/dsh-model-router 0.22.2）是 Alice-Marx 维护的 DSH 插件，面向 Harness Desktop 提供本地任务规划、多模型路由预设、依赖工作包执行与十二种官方 CLI 的发现安装。配置走 Models 页与插件设置，状态存于 ~/.dsh/model-router/state.json。支持只读预览、workspace-write 与 cli-native 可编辑团队等显式权限。安装使用 dsh plugin --profile web/desktop add 指定版本。兼容 Desktop 0.2.0-rc.1/0.2.0-rc.2/0.2.1-rc.2；GAL 已拆为独立插件。
Read Moremodel-auto-router：按任务自动选模型的 Agent Skill
model-auto-router 是 SkillHub 社区 ai-agent 类 Skill，在用户未指定模型或明确要求选模型时，先根据任务从 OpenClaw /model 列表中路由再执行。机制包括关键词快判、陌生模型联网归类与会话内缓存。本文基于 SkillHub 官方简介与安装文档，说明定位、触发方式、skillhub install 安装路径（含 Cursor 等目录）及典型对话用法与注意事项。
Read Moredsh-free-tier-router：把多平台免费 LLM 额度合成可自动切换的渠道池
dsh-free-tier-router 是 EiyoV 维护的 DeepSeek Harness 插件（v1.0.0，MIT）。它在 DSH 内挂载自包含代理，将多平台免费额度与自配 key 合成渠道池，按识图/工具能力过滤、按实测 token 成本排序，并在限流或失败时自动切换。安装可通过 SkillHub 给出的 pinned GitHub 命令或 README 的 profile 安装；数据与密钥位于 ~/.dsh/llm-router/。文章说明核心路由与额度熔断规则、面板用法及「不代注册、付费渠道需 manualOnly」等边界，并提醒安装前审阅源码与插件以 DSH 进程权限运行。
Read Moredsh-model-router：DeepSeek Harness 任务感知型模型路由
DeepSeek Harness 插件 `dsh-model-router` 旨在实现“一切皆插件”，通过任务感知智能路由模型。它根据任务类型（如研究或闲聊）和模型能力，自动调度请求至最优模型，优先保证研究质量或使用免费模型处理闲聊。该插件支持 Grok 限制、速率限制处理、子代理及模式切换，提供 dryRun 验证和详细日志，有效简化了智能体模型维护。
Read Moredsh-plugin-reasoning-effort-sync：自动同步模型推理级别
DeepSeek Harness（DSH）推理努力选择器插件旨在解决自托管或中继网关无法获取 `reasoningEfforts` 元数据的问题。该插件通过同步网关的 `/models` 端点数据，自动将推理努力级别写入配置，支持回退到 `models.dev` 数据集，并提供路由白名单、超时控制及 dry-run 验证功能。安装需 DS Harness 0.2.0-rc.2 版本，默认配置为空字典处理所有路由。
Read Moredsh-plugin-jev-router: Per-Turn Model Routing Plugin for DeepSeek Harness
dsh-plugin-jev-router is a DeepSeek Harness plugin designed to address the cost waste caused by agents sending uniform requests for every conversation turn. By introducing Jev selection questions, it dynamically selects the appropriate model and reasoning effort for each turn. Core features include per-turn routing, escalation for difficult turns, a fast path for simple operations, sticky retention, and receipt logging. Users must configure a Jev API key and a candidate-list YAML to optimize costs and improve inference efficiency.
Read MoreDSH PackyCode API
DeepSeek Harness (DSH) has introduced the PackyCode API plugin, designed to simplify the model invocation workflow. The plugin provides core features such as built-in model routing, automatic multi-key rotation, key selection by group, real-time balance viewing, and local credential management. During installation, a version number must be specified (e.g., `dsh-packycode-api@1.2.9`). It supports adding API keys and selecting models through settings. The plugin is optimized for domestic network environments and integrates with Claude local CLI, image generation, and web search. Keys are stored only in the local credential file to ensure security. It is suitable for developers who need to manage multiple models and API keys.
Read Moredsh-opencode-patch: Make OpenCode Models Available in the DeepSeek Harness
`dsh-opencode-patch` is a plugin designed specifically for DeepSeek Harness to fix the issue where the OpenCode model fails to work under its default configuration. By restoring session affinity, gateway source headers, and providing tool definitions for the free tier, it resolves request rejections caused by missing network-layer protocol support. Additionally, the plugin supports offline caching of model catalogs and a real-time billing dashboard, ensuring that traffic from other providers remains unaffected.
Read Moredsh-smart-scenario-router: DeepSeek Harness Scenario-Based Model Routing Plugin
`dsh-smart-scenario-router` is a plugin for DeepSeek Harness, designed to address the manual model switching issue in multi-model environments. It automatically identifies the scenario based on user message content (such as code writing or everyday conversation), routes requests to the most suitable model, and automatically tries the next model if a request fails, reducing operational costs. The plugin supports prioritizing domestic models and features visual configuration and an automatic fallback mechanism. Installation requires meeting DSH version requirements, while configuration is simple and fully compatible with the existing authentication system.
Read Moredsh-model-router: A Reasoning Effort Routing Plugin for DeepSeek Harness
`dsh-model-router` is a DeepSeek Harness plugin designed to automate the management of model reasoning effort and model switching. It supports Flash-only reasoning effort routing, model pool management (including cost tiers and vision tags), task presets (with keyword matching and weight configuration), and Composer UI integration. It can automatically allocate reasoning effort based on task difficulty and intelligently route models using semantic classification or keyword matching. When using the plugin, thinking mode must remain enabled, and source code modifications require a full application restart.
Read Moredsh-subscription-antigravity: Reusing Google Antigravity Subscriptions in DeepSeek Harness
`dsh-subscription-antigravity` is a DeepSeek Harness (DSH) plugin maintained by shaomingbo, designed to simplify the access process for users with existing Google Antigravity (AI Pro/Ultra) subscriptions via a local OpenAI-compatible loopback proxy. The plugin uses browser-based PKCE login authorization and supports multi-account pool management, quota viewing, and instant switching. It encapsulates models such as Gemini, Claude, and GPT-OSS in Cloud Code Assist as the `antigravity` route in DSH. DSH must be manually restarted after installation. The plugin is unofficial; credentials are securely stored, and authentication files must be manually deleted after uninstallation.
Read Moredsh-adaptive-model-router: DeepSeek Harness Per-Turn Adaptive Model Routing
dsh-adaptive-model-router is a deterministic plugin for DeepSeek Harness that automatically switches between an “economy model” and a “high-quality model” based on task complexity. By performing local computations (such as character count, keywords, and step count) within a single session, it enables model upgrades while maintaining a balance between low cost and high quality. It requires no extra model calls, supports configurable upgrade conditions, and is well suited to scenarios where complexity changes dynamically.
Read Moredsh-model-router: Introduction to the DSH Plugin
dsh-model-router is a plugin based on the DeepSeek Harness (DSH) concept, designed to address management challenges in multi-model scenarios. It maps virtual model IDs to a candidate model pool and uses algorithms such as priority or round-robin to achieve transparent failover. Users can manage routing logic through configuration files without modifying code, and the plugin automatically switches models when streaming responses fail. It supports response source tracking and includes a built-in test suite, suitable for Node.js 22+ environments.
Read MoreDSH Model Management Plugin: Unified Model Visibility and Routing
`sharewiner/dsh-model-management` is a DSH Web profile plugin designed to streamline the cumbersome operations in OpenAI-compatible model management. It provides a centralized management interface, supports configuring default models, and controls the visibility of models and providers. It also includes web search routing functionality. The plugin accesses DSH services through a compatibility layer without storing keys. It is currently in early access and requires a Node.js 22.19+ environment.
Read Moredsh-model-switch: Explicit Model Routing for DeepSeek Harness
The dsh-model-switch plugin for DeepSeek Harness (DSH) provides an explicit model routing mechanism for fine-grained control of model selection in scenarios such as the main model, subagents, web search, image generation, and plan approval. The plugin includes an interactive selector, model variant grouping, and supports automatically compressing oversized conversation history when sending messages. Configuration requires Providers to publish models to the Catalog; it does not support silent fallback, and invalid routing will directly result in an error. In addition, the plugin does not interfere with official Agent presets, credentials, or core-layer runtime.
Read Moredsh-subagent-router: DeepSeek Harness Subagent Model Routing Plugin
The `dsh-subagent-router` plugin provides DeepSeek Harness with more flexible subagent model selection. It uses the `subagent_model` tool to allow explicitly specifying the Provider, Model, and output limit at invocation time, or to apply the built-in `model:"auto"` automatic model-selection strategy. This strategy includes task tiering, health awareness, and failure escalation. The plugin also offers `subagent_models` model directory lookup and `subagent_recommend` intelligent recommendation features. It is simple to install and takes effect immediately, primarily addressing the limited flexibility of standard routing inheritance.
Read MoreFreeDSH (dsh-h-v1): Free Routing and Security Update Plugin for DeepSeek Harness
FreeDSH is a community-maintained plugin for DeepSeek Harness, designed to mitigate high single-model costs and environment fragility through free-first multi-model routing and local gateway integration. It offers core features including intelligent failover, UI overlays, secure core updates, and versioned overlays. Users can install it on Windows or Linux using the provided commands, or as a Bundle, and rely on snapshot and rollback tools to maintain environment stability. The plugin requires locally managed credentials and is not affiliated with the official DeepSeek team, making it well suited for users focused on cost control and configuration management.
Read Moredsh-model-controller: A Dynamic Model Routing Plugin for DeepSeek Harness
`dsh-model-controller` is a plugin for DeepSeek Harness, designed to automatically select the appropriate model and reasoning intensity through keyword and semantic classification, replacing cumbersome manual switching. This plugin supports mixed, semantic-only, and regex-only matching modes, and provides dedicated routing for Plan Mode. Installation requires compliance with Node.js and Harness version requirements and configuration in the settings. The default rules cover scenarios such as complex structures, code reviews, and small scripts, significantly reducing maintenance costs and improving task suitability.
Read Moredsh-adaptive-model-router: Adaptive Model Routing for DeepSeek Harness
`dsh-adaptive-model-router` is a model inference plugin under the DeepSeek Harness (DSH) ecosystem. It is designed to automate model parameter configuration and reduce development costs through adaptive discovery, evaluation, tiering, and subagent routing. The plugin supports dynamic model resource management and scheduling. It is recommended to carefully inspect the source code and license security before installation.
Read MoreDeepSeek Harness Subagent Model Routing Plugin: Automatically Route Flash and Pro
The dsh-delegate-router plugin addresses the excessive costs caused by DSH subagents inheriting the parent model by default (such as Pro). It automatically routes lightweight tasks to the Flash model and keeps demanding tasks on the Pro model based on task characteristics, with support for custom rules, manual overrides, and decision logging. The plugin takes effect without a restart, significantly reducing inference costs through model routing.
Read MoreDSH Plugin: satan9394/dsh-model-gateway
satan9394/dsh-model-gateway is a model inference routing plugin within the DeepSeek Harness (DSH) ecosystem. It aims to address multi-model management, cost control, and intelligent routing. The plugin supports over 290 providers, includes 19 built-in routing strategies with fault-tolerance mechanisms, and provides RTK+Caveman compression to save 15-95% of inference resources, along with a free-tier budget feature. Since there is currently no official installation command, users need to obtain it through the ecosystem catalog or from the source code. It is suitable for DSH users who need to integrate multiple providers and control costs, but they should review the source code and license before installing.
Read Moredsh-quota-router: DeepSeek Harness Pure-Policy Multi-Source Model Router
`dsh-quota-router` is a purely policy-driven multi-source model routing plugin for DeepSeek Harness (DSH), designed to address the difficulty traditional routing has in distinguishing subtask types by leveraging "task profiles" and "candidate chains." The plugin builds candidate chains using global priorities and mappings, supports health checks, fallback mechanisms, and observability, and is primarily intended for cost source management in mixed workflows. After installation, routing policies are configured through a Web interface to ensure deterministic routing decisions.
Read MoreDSH Smart Model Router: A Configurable Intelligent Model Routing Plugin for DeepSeek Harness
`dreamzhongju/dsh-smart-model-router` is a DeepSeek Harness plugin that simplifies multi-model integration and switching through automation. It provides intelligent classification and routing, directs requests to predefined configurations, and performs sequential failover when the primary model is unavailable. It supports reading configurations from local directories, does not store credentials, and takes over model selection in non-manual modes. Easy to install, it is ideal for users who need fine-grained control over model invocation policies.
Read MoreDeepSeek Harness (DSH) Model Routing Plugin
`welsione/dsh-model-router` is a DeepSeek Harness (DSH) plugin built on the “everything is a plugin” design, intended to unify management of logical model IDs across multiple providers. It aggregates multiple candidate models into a single logical entry point and supports three-tier prioritization, first-token automatic failover, and health-based best-model selection. The plugin offers multi-plan routing, intelligent cooldown, thinking-level configuration, an admin panel, and bilingual support. After installation, users can configure models centrally in DSH settings; the plugin automatically persists the configuration and ensures safe runtime operation, effectively reducing the complexity of multi-provider model invocations.
Read Moredsh-kernel-mesh: DeepSeek Harness Multi-Kernel Model Routing Plugin
`dsh-kernel-mesh` is a kernel mesh plugin for DeepSeek Harness (DSH) designed to enable seamless switching across multi-model collaboration. It packages the Kimi, Grok, Codex, and MiniMax models as plugins, providing model routing, subagent recipes, and management tools that support checking status, dispatching tasks, and switching routing paths. Installation requires adding the plugin itself and each model kernel dependency separately, along with manually configuring agent presets. The plugin supports fallback routing and vendor-specific search tools, with each kernel having its own independent system prompt. With this plugin, users can uniformly manage multi-vendor models and subagents within DSH.
Read Moredsh-tui-model-switch: dsh-TUI Subagent Model Routing Plugin
dsh-tui-model-switch is a dsh-TUI plugin maintained by FUSU123fusu that enables subagents to use independent model configurations. Users can specify a custom provider, model, or reasoning effort for subagents through the /settings interface, with changes taking effect in real time. The plugin is open source under the MIT license, although it requires restarting the DSH service for the effect. Its working mechanism includes priority-based overrides and intercepting only subagent sessions, while model routing during the plan execution phase is not currently supported.
Read MoreDeepSeek Harness Intelligent Delegation Suite (dsh-delegation-suite)
`dsh-delegation-suite` is a DeepSeek Harness (DSH) plugin focused on intelligent agent task delegation. Its core features include a role-based routing mechanism and automatic model failover (mutual backup), along with context inheritance (Fork delegation), visual configuration, inline thinking-intensity adjustment, and token balance monitoring. The plugin provides a Web GUI for editing routing tables, supports image transcription and multiple strategy prompts, automatically tracks usage, and queries balances across platforms. Installation should be handled carefully to avoid configuration conflicts. It is suitable for development scenarios that require fine-grained control over model allocation and cost monitoring.
Read Moredsh-swarm-router: DSH swarm plugin for routing heterogeneous tasks to the most suitable model
Introduction: In agent development, you often encounter task batches like this: one involving 17x23 arithmetic problems, another requiring code writing and prime number verification, and a third being long-form translation. Sending them all to the same model queues simple tasks on flagship models, wasting time and tokens; assigning difficult tasks to cheap models often leads to errors. Manually selecting a model for each task becomes unmaintainable as the workload increases. dsh-swarm-router addresses this problem: it organizes a batch of heterogeneous tasks into a "Sub-Agent Matrix Swarm"—tasks are rows, and candidate models are columns. The router selects one cell for each row, and then uses DSH's `ctx.subagents` to turn each cell into a process-bound sub-agent parallelized to the selected model. # What is dsh-swarm-router
Read Moredsh-cc-switch: One-click sync cc-switch transit merchant configurations to DSH model routing
# Introduction Running agents with DeepSeek Harness (DSH) inevitably involves model configuration. If you have been using cc-switch to manage proxy configurations for Claude Code / Codex, these ready-made providers cannot be used directly within DSH. The conventional approach is to manually re-enter API addresses and keys in DSH and set up the routes. dsh-cc-switch is designed to solve this: it enables a one-click synchronization of the provider configurations managed in cc-switch into DSH's model routes, without requiring any models to be pre-configured in DSH. In other words, a brand new DSH instance with zero models can get started using your existing providers via this tool. DSH's philosophy is "...
Read Moreoh-my-dsh: DeepSeek Harness Layered Model Routing Plugin for think/build
# Introduction There is a common dilemma when running agent coding sessions: running the strongest model at every step is effective but costly and slow, whereas using cheap models throughout cannot handle complex tasks like planning and architecture design. Manually switching models between sessions is equally cumbersome and interrupts the flow of thought. oh-my-dsh solves this problem: it implements model tiering within a single DeepSeek Harness (DSH) session, using strong models for planning and cheaper models for daily execution, with dedicated channels for image understanding and image generation. This eliminates the need for manual session switching or YAML editing. The following sections introduce its features, installation methods, and typical usage. # What is oh-my-dsh? It is a DSH plugin maintained by llmpolska under the MIT License. The current version is...
Read Moredsh-shift-router: DSH's two-level model routing plugin
`dsh-shift-router` is a two-level model routing plugin for DSH, designed to intelligently allocate model usage for daily and critical cycles. It classifies requests into `fast` or `smart` tiers via an LLM Judge, adopts a strategy of "instant upgrade, trend downgrade," and pauses switching during Prompt Cache hotness to optimize costs. The plugin supports runtime failover, implementing exponential backoff cooling during service exceptions and switching only healthy models within the same tier. It also features task-level orchestration, allowing strong models to plan and delegate tasks to weak models for execution, with enforced task limits. Additionally, it provides per-tier token and cost telemetry. Installation requires Node `>=22.0.0`, and the routing mode (auto/manual/off) can be adjusted via GUI or command after configuration.
Read Moredsh-model-router: Add virtual model providers to DSH and route requests based on active providers.
`dsh-model-router` is a community plugin for DSH designed to address management pain points in multi-provider and multi-model configurations. By registering a virtual provider named `model-router`, it aggregates models scattered across various providers into a single selector, supporting strict merging based on model IDs. Users can view the available providers for each model in the model selection menu or settings card, and support one-click switching of the currently active provider as well as drag-and-drop adjustment of priority order. The plugin adopts a real-time routing mechanism, preserving the virtual provider identifier within the session and resolving/delegating to the currently active real provider only when an LLM request is issued, ensuring consistent routing logic for main agents, sub-agents, and tool calls. The plugin features automatic synchronization capabilities, allowing it to automatically clean up configurations and fall back to active states when new providers or models are added or removed. It is suitable for Web, C...
Read Moredsh-subagent-model-router: Optional Models and Routing Configuration for DeepSeek Harness Subagent
`dsh-subagent-model-router` is a plugin designed for DeepSeek Harness (DSH) to unify the management of model routing, delegation, and background result aggregation for sub-agents. This plugin addresses the issue of scattered configurations caused by the varying model capability requirements for different tasks (such as retrieval, reasoning, and review). Core features include: the `subagent_model` tool restricting model selection to configured aliases; the `wait-for-subagents` tool used to wait for terminal results from background sub-agents; embedding model tags and routing instructions into system prompts to assist orchestrator decision-making; and providing a read-only model directory view as well as namespace-scoped configuration tools. Additionally, it supports manual routing management via a Web settings page and configuration in `~/.dsh/settings.yaml`.
Read Moredsh-auto-model-router: L0–L3 Model Routing for DeepSeek Harness
dsh-auto-model-router is a third-party model routing plugin for DeepSeek Harness (DSH) designed to address the trade-off between cost and effectiveness caused by significant disparities in model capability requirements across different requests. By registering a virtual `auto` provider, this plugin intelligently routes requests to four capability tiers (L0–L3) and supports three user modes: heuristic lock, fixed tiers, and fully-auto. Its core features include zero-latency heuristic locking based on text width, configurable-weight keyword scoring, an optional LLM classifier, a failure fallback chain, and budget control strategies that prioritize cost, quality, or balance. When a real model is explicitly selected, the plugin does not interfere with routing, allowing the request to pass through unchanged. This plugin requires Node version ^22.19.
Read Moredsh-legion: DeepSeek Harness's Multi-Agent Delegation and Model Routing Plugin
dsh-legion is a TypeScript multi-agent orchestration and LLM model routing plugin designed for DeepSeek Harness (DSH), aiming to extend existing runtime capabilities rather than introducing an independent framework. Its core mechanism delegates delegation strategies to deployment-side configuration; coordination agents select semantic Specialists (such as 'quick', 'deep', 'review') solely through the `legion` tool, while specific model routing, backend types, tool filtering, depth, and result contracts are determined by plugin configuration. This plugin supports precise multi-provider model routing, multi-sub-agent backend strategies, structured versioned result output, custom Cohorts, and declarative Strategies, and features hard resource limits and explainable diagnostics.
Read Moredsh-opencode-go-provider: OpenCode Go Provider Plugin for DSH rc.6
`dsh-opencode-go-provider` is an MIT-licensed plugin maintained by `edynasty`, designed specifically for DeepSeek Harness (DSH) `rc.6`. It provides `opencode-go` model routing, a Web Connect settings card, a stale-while-revalidate model directory, and security diagnostic commands. This plugin is not published to npm and requires installation into the DSH `web` profile via a Git dependency pinned to a specific commit. The runtime environment requires Node.js `^22.19.0 || >=24.0.0`, pnpm `11.7.0`, and a valid OpenCode Go API key, the latter of which is only accessible via...
Read Moredsh-switch: A Model Control Plane Plugin for DeepSeek Harness
dsh-switch is an evidence-first model control plane plugin for DeepSeek Harness (DSH). It provides two independent functions: first, within DSH, it checks registered Provider routes and the default model via `dsh_switch_status`, and verifies and saves the default model settings for new sessions via `dsh_switch_default`, affecting only new sessions and never intercepting or rerouting active session requests; second, it offers a standalone CLI tool for read-only probing of OpenAI-compatible `/models` endpoints, reporting reachability, HTTP status, latency, model counts, and credential configuration status, without consuming inference tokens or verifying end-to-end generation capability. The plugin emphasizes security boundaries and rejects embedding...
Read Moredsh-model-router: A Thin Routing Strategy Plugin for DeepSeek Harness (DSH)
dsh-model-router is a thin routing policy plugin for DeepSeek Harness (DSH), version v0.2.2, licensed under the MIT License. It adds rule execution on top of DSH's existing model management, with core features including deterministic keyword routing, the whitelist-based model switching tool `model_route` that is disabled by default, and an isolated Beta image generation channel `image_gen`. Routing rules are executed in configuration order, stopping at the first match, while preserving the current state if no rule matches; model switching requires precise validation of provider, model, and other fields. `image_gen` uses an OpenAI-compatible endpoint, enforces HTTPS and strictly restricts result downloads, and supports integration with third-party services such as Seedream; however, video, audio, and 3D features are not included.
Read Moredsh-model-router: Model Routing and Cost Dashboard for DeepSeek Harness
`dsh-model-router` is a model routing and cost optimization plugin for DeepSeek Harness. It routes simple requests to cheaper models through heuristic rules, reserves complex requests for the main model, and automatically falls back on instantaneous failures. This approach reduces costs while ensuring quality for requests requiring context, vision, or reasoning capabilities. The plugin supports vision-aware routing, prioritizing available vision models if messages contain images, and respects user-selected models. In automatic mode, it prompts the user for a quick response when a simple request is detected. Additionally, it provides a real-time panel in the Composer Dock, displaying token usage, cache hits, and estimated costs based on the pricing table. Installation requires ensuring the `dsh` CLI is in the PATH, followed by restarting the Web profile.
Read Moredsh-tier-router: Hierarchical Model Routing for DeepSeek Harness
`dsh-tier-router` is a hierarchical model routing plugin for DeepSeek Harness (DSH), designed to optimize cost and efficiency through "premium-tier" and "economy-tier" strategies. The premium-tier models handle complex tasks such as planning, architecture, and review, while the economy-tier models manage routine implementations. Core features include automatic hierarchical routing (defaulting to `auto` mode), session-level scope switching, on-demand consultant and review tools, automatic escalation on failure, ordered fallback chains, dynamic adjustment of reasoning intensity, gating for high-impact operations, and hierarchical delegation to sub-agents. The plugin supports flexible configuration of models, effort levels, and sub-agent strategies via `/tier` series commands, with both persistent and temporary configuration capabilities. Released under the MIT license, installation requires meeting specific Node.js version requirements and syncing to the DSH discovery root directory. It is suitable for applications needing
Read More《Cursor Docs》-Cursor Router
Cursor Router is the model routing system behind Auto . Not every request needs frontier level intelligence, so the router sends each request to the model that fits the task: simple requests go to fast, efficient models while complex work goes to the most capable ones.
Read MoreUse dsh-model-router to implement model routing and cost dashboard for DeepSeek Harness
`dsh-model-router` is a DeepSeek Harness web plugin maintained by *tianji-qingtian*. It directly answers simple questions after verification by the Flash Judge, automatically downgrades when instantaneous failures occur, and displays token counts, cache hit status and estimated costs below the input box. This article verifies the installation commands, `/router` usage and known limitations by cross-checking with the directory page and GitHub README/source code.
Read MoreOmniRoute Sees Over 9,000 Star Gains in a Week: Unifies 290+ Model Providers via Local AI Gateway
OmniRoute (diegosouzapw/OmniRoute) is one of the open source projects with the fastest growth in stars in the GitHub AI Agent category in July 2026, with an increase of approximately +9,200 in 7 days. This MIT-licensed local AI gateway aggregates over 290 model providers (including over 90 free tiers) through a single OpenAI-compatible endpoint, with built-in Combo automatic fallback, quota-aware routing, cost telemetry, and support for MCP/A2A. It can connect to programming agents such as Claude Code, Cursor and Codex. This article introduces the pain points of multi-model switching it solves, the core routing mechanism, quick start steps, as well as the security and trust boundaries during deployment.
Read More