Plugins

ModelTester — model detection & attribution panel for the DeepSeek Harness web chat. Ranks vendor families (DeepSeek / Anthropic / OpenAI / Google / Qwen / GLM / Kimi / MiniMax / MiMo / LongCat / InternLM / Step / Yi / Llama / Mistral / Nemotron / Grok /

Free web search for DeepSeek Harness: 19 engines (Bing/DuckDuckGo/AnySearch/SearXNG/Exa/Tavily/Keenable/Firecrawl/Parallel keyless; Perplexity/SerpBase/DeepSeek/You.com/Baidu/Kimi/Aliyun/Doubao with key) + OpenAI model built-in web search + adjustable pri

Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weaving 35 DSH Web endpoints into 16 voice-friendly tools for workspaces, sessions, chat, models, settings and files — outbound WebSocket to the Xiaozhi MCP access point by default (no public IP or port forwarding needed), several devices bound at once, plus a DSH settings page with live status.

Read-only side branch in the right sidebar: quote text to ask follow-ups without polluting the model context of the main session; every follow-up rebuilds the branch from the latest settled turns of the main session, and writes are refused at the tool-execution layer so the prompt prefix stays cacheable.

DSH 临时任务模式：为 DSH 增加「任务」分组——不绑定任何长期工作空间，自动在任务根目录下创建隔离的临时工作目录并开启会话，即开即用、用完即弃。Temporary task mode for DeepSeek Harness.

DSH 模型整理插件：输入框的模型下拉改为「供应商分组 + 模型二级折叠菜单」（含推理等级），并在模型设置页提供一个可拖拽的「供应商与模型顺序」浮窗。

Jev (TypeSafe System One) gives the human a second opinion, not the agent. When DSH's model asks you a multiple-choice question, dsh-jev-advisor builds a structured Jev request and floats the recommendation, probability spread and confidence beside the op

Universal MCP Apps Host & UI Plugin for DeepSeek Harness (DSH)

Free OpenCode Zen models in DeepSeek Harness through native HTTP requests. No OpenCode installation, login, API key, server, container, or LiteLLM is required.

A structured decision layer for the DeepSeek Harness agent loop: a danger-call gate, output self-check, tool narrowing, and loop guard backed by a pluggable adjudication model.

Local TXT reader in a right-sidebar tab plus a spoiler-safe AI reading companion: the model only sees what you have already read — the current chapter, the tail of the previous chapter, and a per-book background file it grows as you go. Excerpts, thoughts and the companion replies become structured Markdown notes exportable to Obsidian; raw text unlocks only for a book you mark as finished.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Paper library and reading workbench: arXiv search, a local plain-file library (metadata / PDF / extracted full text), and three-level reading notes (overview / understanding / critique) kept as markdown beside the PDFs; seven model tools plus a web panel.

Just Pin a model to Favorites, so you dont need to choose it from menu. (Dsh plugin)

DeepSeek Harness (dsh) plugin: live local LLM endpoint health in the web rightbar. llama.cpp slots (busy/TTFT/wedged, /metrics) + Ollama MODELS (loaded vs empty). Engine fingerprinted by response shape. Installable dsh.bundle.

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

DeepSeek Harness plugin that asks which provider and model should run each delegation before the child starts, so a subagent can go to a cheap or local route instead of the parent's.

DeepSeek Harness (dsh) plugin that connects Sber GigaChat models: a built-in local OAuth proxy (client-credentials -> OpenAI-compatible endpoint, upstream serialization, legacy tool-calling translation) plus automatic provider-route bootstrap, so GigaChat

DSH bundle: WeChat floating-ball bridge (QR login, message relay, ClawBot model config) — maintained fork of lubaiUwU/DSH-WeChatClawBot

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, hidden-models blacklist, live per-task cost, prices and context windows, a refresh button that re-syncs every provider model list from its live API, and the

Keep DSH provider model catalogs current with the living models.dev catalog: refreshes each provider's models (new and existing) with updated modalities and thinking levels — automatically and from one refresh button in the Models page. / Utrzymuj żywy ka

Measure whether a dsh setup change actually helped: register repeatable cases, run them, and diff the results before and after you change rules, skills, or models.

Track token spend and enforce budgets for every model call your dsh agent makes.

Run the same prompt through every model you have, and see the difference without squinting.