dsh-file-upload
GLFzr
DSH 拖拽文件转路径插件:Codex 式拖拽,路径自动插入输入框(Drop File to Path for DeepSeek Harness)
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。
153 个项目,匹配「rag」
GLFzr
DSH 拖拽文件转路径插件:Codex 式拖拽,路径自动插入输入框(Drop File to Path for DeepSeek Harness)
Tianbuyu-wwx
FormatForge — DeepSeek Harness plugin: drag any file (PDF/DOCX/XLSX/EML…, 30+ formats) into dsh and it becomes AI-readable structured data. npm: @tianbuyu-wwx/dsh-formatforge
GGboya
DeepSeek Harness (dsh) 插件:论文伴读工作台 —— PDF 转录 / 检索 / 流式问答 + 内置阅读器页面。
lhh010
DSH WebUI 文件输入增强:Ctrl+V 粘贴 + 拖拽 + 选择文件(图片悬停预览 / 缩放查看器 / 防伪造校验),发送时复制进会话工作区临时目录;无视觉模型发送失败自动移除图片附件并提示重发;桌面端经 base64 通道可用
meto-ventus
🐳 蓝色大肥鱼 · DeepSeek 虎鲸 3D 桌宠插件 — 由 DeepSeek 虎鲸 logo 轮廓重建,悬浮于 Web GUI 角落:拖拽旋转、360° 转圈、爱心互动、悬停工具栏、大小/灵敏度/文字设置,配置本地持久化 / A 3D whale desktop pet rebuilt from the DeepSeek whale logo for DeepSeek Harness — drag to rotate, 360° spin, heart bursts, hover toolbar, size/sensitivity/caption settings, and local persistence.
Guojiz
Git-native AI learning OS with a GitLearnOS-exclusive DeepSeek Harness panel, targeted practice, local RAG, and learner-owned memory.
No-PRM
DSH plugin: VS Code-style file-tree explorer (git decorations, preview, diff, drag-to-reference); install via dsh plugin --profile web add.
charrywhite
Sticky notes for DeepSeek Harness: draggable notes with text & image support, 9 skins, and AI-powered read/write. DeepSeek Harness 便签插件:可拖拽,支持文字与图片、9 款皮肤,AI 可读写。
huashenglian
给 dsh 对话区叠加 B 站风格吐槽弹幕,可接入 LLM 生成弹幕。/Bilibili-style live-chat danmaku overlay for DeepSeek Harness Web — preset packs, optional LLM quips, drag ball, per-session pools.
leeclouddragon
A local six-max Texas Hold'em plugin for DeepSeek Harness — play with Tokens while your agent thinks.
H1a3x
Floating draggable token usage statistics panel for DeepSeek Harness
PianoPrince
拖拽真迁移 DSH 会话跨工作区:批量移动、分组合并、挂错归位、回收站、备份恢复 + 对话内 agent 工具;步步备份可回滚,零 token / True migration of DSH sessions across workspaces: bulk move, group merge, misfiled homing, recycle bin & backup restore + conversational agent tools; every step backed up, zero tokens
WJZ-P
DeepSeek Harness plugin. 支持直接把图片、文件等拖入到dsh中。更方便地拖拽;image & file drop.
Xiaofei-fei
Bash-like prompt history for the DSH web composer: Up/Down arrows recall previously submitted messages, sourced from the session's own message log (zero config, zero extra storage).
ai-eks
Organize unlimited conversation tabs into editor-style, drag-to-split groups for DeepSeek Harness Web.
AKS1st
DSH 生态中最好的文件浏览插件:VSCode 资源管理器级目录树、新建/重命名/复制粘贴/删除、拖放导入、粘贴本地文件与剪贴板图片、上传进度条与右键菜单;依赖 dock 基座 | The best file explorer for DSH: VSCode-level directory tree with new/rename/copy-paste/delete, drag-and-drop import, paste local files and clipboard images, upload progress and context menus; requires the dock base
Apageoflove
DeepSeek Harness 插件:确认改动的代码行真的被测试覆盖到,结论绑定代码指纹,代码一变自动过期
Awu12277
DSH Web 的定时发送插件:在输入框右侧提供「定时发送」按钮与配置面板,支持智能时段、自定义日期时间、多个定时任务,并通过 localStorage 持久化任务,刷新页面后自动恢复。
Fisfzy
Zotero 文献采集入库插件(DSH external plugin):多源检索(OpenAlex/arXiv/Crossref/Europe PMC/Semantic Scholar)+ OA 下载链接解析(Unpaywall)+ 充分性审计 + 入库本地 Zotero + 触发 zotero-wave-rag 重建
Signalight
Convert Codex desktop pets (spritesheet atlases) into DeepSeek Harness (DSH) web-GUI pets — zero-dependency renderer, drag/wave/jump interactions, live activity poses & progress bubbles. 把 Codex 桌宠移植为 DSH 网页桌宠的通用框架
SoDaZilla-zzz
Draggable liquid-glass DeepSeek API balance card plugin for DeepSeek Harness (DSH) web GUI / DSH ??????? DeepSeek ??????
TecFancy
Learning assistant extension for DeepSeek Harness (dsh): brings DeepTutor tutoring to your agent — deep explanations, self-test questions, learning paths, personal knowledge-base search (RAG), and note archiving. | 面向 DeepSeek Harness 的学习辅助扩展:为 agent 接入 DeepTutor 辅导能力 —— 深度讲解、自测题、学习路径规划、个人知识库检索(RAG)与笔记归档。
lbl61
把文件拖入/粘贴到 DeepSeek Harness Web:输入框原生引用气泡,随消息发送(含绝对路径),气泡渲染文件卡片。Drag/paste files into the DeepSeek Harness web GUI as native reference bubbles — absolute paths, file cards.
rainow
DSH的简化版llm-wiki记忆插件,纯md文档。A lightweight long-term memory framework for DeepSeek harness, simplified LLM-Wiki. No RAG, no vector DB, no LLM calls at runtime. Just Markdown + git.