dsh-commandcode-provider
Mars-Sea
Command Code provider plugin for DeepSeek Harness (dsh). Adds Command Code model access, live model catalog, plan-aware model selection, reasoning effort, image input, web search, and multi-account support.
DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。
33 个项目,匹配「selection」
Mars-Sea
Command Code provider plugin for DeepSeek Harness (dsh). Adds Command Code model access, live model catalog, plan-aware model selection, reasoning effort, image input, web search, and multi-account support.
luobosibing2
Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev as a System One decision layer for agent selection, supervision, corrections, and approvals.
Blank-not-black
DSH Remote · 口袋里的 DSH 控制台 会话 · 审批 · 提问 · 文件传输,局域网 / Tailscale 直连 多服务器自动选优,聊天记录离线可看 带 Token 鉴权,数据只在你的设备之间流动 Sessions · approvals · questions · file transfer over LAN / Tailscale. Automatic fastest-server selection. Chat history available offline. Token-authenticated — your data flows only between your devices.
SeverusZh
Subagent Director: per-subagent LLM provider/model selection with role templates for DeepSeek Harness (dsh plugin)
g-yixuan
侧边开一岔对话,划选留一条注释——DSH(DeepSeek Harness)插件:fork 主会话成侧边会话,支线问题不打断主线,结论一键回流。Side chat & selection annotations for DSH.
labmimors
Search 1,000 MCP tools through two interfaces in DeepSeek Harness. Load exact schemas on demand and keep structured results usable across tool calls.
Shrbuz
Floating notes for the dsh web GUI: keep commands, credentials and snippets at hand, insert any note into the composer, save any selection as a note
Nzssm1
A DeepSeek Harness (DSH) agent preset for institutional multi-factor stock-selection research: methodology knowledge base + zero-dependency factor statistics.
wangwei-wade
DSH 会话选区引用与锚点批注插件:选中文字 → 批注 → 引用锚点 chip(点击跳回原文、悬停显示原文)。Contextual selection & anchored annotation plugin for DeepSeek Harness.
JuneLearn
让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度,并可为每次子 Agent 调用选择模型|Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call
MichengAI
DSH Code Review — 为 DeepSeek Harness 提供 Codex 风格代码审查、原生独立子 Agent、灵活范围选择和中英文报告 · Codex-style code review with native independent agents, flexible scope selection, and bilingual reports for DSH
TaurenMountain
LLM-as-a-Verifier for DeepSeek Harness: fine-grained reward, Probabilistic Pivot Tournament best-of-N selection, and per-step progress tracking as agent tools.
lzbaclz
ChatGPT-style select→ask for DeepSeek Harness Web: select text in a conversation, a floating 「询问 DeepSeek」 button appears — click it to quote the selection into the composer.
ZoeHao2026
Accessible collapsible provider groups for the DeepSeek Harness model selector.
suiyideali
在 DeepSeek Harness 会话里划选文本,选区上方浮现一个小工具栏: 复制 · 引用 · 询问 · 解释 · 翻译 · 总结 · 自定义。 所有 AI 动作都复用当前会话——选中文本作为普通用户消息注入当前对话, 模型带着完整上下文作答。
QIN-SMART
Select text in a DSH reply: a floating toolbar that quotes it into the composer draft or opens a side chat about it.
nekogpt
Codex-style select-to-quote for DeepSeek Harness Web: quote any chat text into the composer as a native reference chip.
yuanc1204
Codex-style multiple independent selection comments for DeepSeek Harness (DSH).
AlexKaiqi
Model catalog, portraits, Agent selection, and multimodal runtimes for DeepSeek Harness
ChadCSong
Auto-discovery CLIProxyAPI provider for DeepSeek Harness, featuring dynamic model sync, native model switching, and vision-model selection.
FraYoshi
Invert selection in Deepseek Harness for when we are selecting models
JasperGuWP
DeepSeek Harness plugin development rules: five extension forms (bundle / patch plugin / preset / skill / dynamic plugin) with a selection decision tree, install & publish guide.
PhysicalAI-0
PaperForge — forge your understanding of papers inside DSH: selection-to-highlight, selection-to-ask (one dedicated session per paper), marquee-to-note screenshots with backlinks.
bxsexc
DeepSeek Harness native plugin: Settings UI for the Roblox Studio MCP bridge - list connected Studio instances, pick the active one, and expose the selection to agents as runtime context.