dsh-paste-to-path
Johnny-xuan
A universal path-backed attachment dock for DeepSeek Harness . ( Unmaintained/Deprecated )
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。
199 个项目,匹配「ava」
Johnny-xuan
A universal path-backed attachment dock for DeepSeek Harness . ( Unmaintained/Deprecated )
YOGEMOW
为纯文本模型按需识图:DSH 零补丁 Cordis 插件(prism_see 工具 + 图片 VEP 降级 + 技能运行时注册)+ Codex Skill;多 Provider 视觉 API,VEP/1 低 Token 视觉证据包
a1073097082
该仓库暂未提供项目说明。
bearllfleed
给 DeepSeek Harness (DSH) Web 界面加一个 VS Code 风格的工作区文件浏览器:右侧文件树 + 可编辑标签页 + Markdown 阅读/编辑/分屏 + 悬浮大纲 + Quick Open 搜索。
grelvan
DeepSeek Harness 本地 OCR 插件:粘贴图片,PP-OCRv5 + ONNX Runtime 识别文字,完全离线 | Local OCR plugin for DeepSeek Harness — paste an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline.
gugu123a
see_image tool for DSH: lets text-only models 'see' images by routing them to a configurable vision model (default Zhipu GLM-4V-Flash, free)
kbpoyo
DSH 插件:让纯文本模型也能看图。Web 端直接粘贴图片即可发送,无需指定图片路径;模型自主调用视觉技能查看,多模态模型原生直通,零skill绑定。
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.
paicat1
DSH 轻量截图插件:轻 : 纯 PowerShell 实现,零依赖、零二进制;截图能力独立维护,不随任何上游更新而失效。 摆 :一键全屏即拍;框选前整个桌面保持可操作,所有窗口像布置画面一样自由移动、缩放;鼠标悬停任意窗口即亮起吸附边框,点一下直接截该窗口,被遮挡也能拿到完整内容,所得即所见。 自助:Agent 可随时自行截屏;接上 modlens(选装),截屏 + 识图一步产出结构化内容(OCR/版面/语义),纯文本模型也能消费。
121103qwq
Hosted free vision sidecar for DeepSeek Harness with durable session evidence
ByronLeeeee
Matter-aware legal workspace dashboard and document agent tools for DeepSeek Harness
Nothree-code
Workspace file-tree panel for the DSH web UI: explore, preview (DOCX / Markdown / PDF / code / CSV), and manage files with a real context menu.
Sorwcyra
Paste images into DeepSeek Harness with a four-model vision race, OCR, and an automatic text bridge.
VAST-AI-Research
Tripo 3D plugin for DeepSeek Harness (dsh): text/image → textured, rig-ready 3D assets via tripo-cli
Walvez
DSH provider-level web search failover pool: 8 free/paid backends with quota-aware circuit breaking (keeps native web_search)
linkingoscar
Codex-style attachment formats for the DeepSeek Harness Web GUI: PDF text-layer extraction, Office text extraction, scanned-PDF OCR, long-document spill + index cards, image-to-PNG.
tdf1995
Vision for text-only LLMs in DeepSeek Harness (DSH): describe images / OCR / VQA via free Gemini & GLM vision APIs
xiaozhe7772222
Universal image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint. Supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more. | DeepSeek Harness 统一绘图路由器
xing666173
DeepSeek Harness EAC 视觉全家桶:15 个像素级视觉工具(增强版 dsh-tool-vision)+ 桥接内联预览 + 拖拽文件上传,单端点驱动,对话干净,EAC 原生设置适配
1HelloMan1
DeepSeek Harness usage dashboard with API balance, daily spend, external vision-call accounting, per-model stats, call logs, cache rate, TTFT, and CSV export.
240xu
Unified web search provider for DSH
Medesol
Kimi (Moonshot AI) official Formula API tools for DeepSeek Harness — web_search via kimi-official provider + 10 kimi_* tools, no DeepSeek/Exa/Perplexity key needed
SiriusWJ
跑团 / DM 工具插件(DeepSeek Harness):中立随机裁决 + 本地 ComfyUI 配图 + 按会话隔离的战役配置(角色卡 / 世界 / 随机表)。TTRPG/DM tools for dsh: dice, local ComfyUI illustrations, per-session campaign state.
Terry12138qy
DeepSeek Harness 识图插件:为不具备原生识图能力的模型提供识图能力(阿里云百炼 qwen3.5-omni-plus,失败自动切换智谱 glm-4.6v-flash)。由 claude-vision-skill 移植适配。 | Vision tool for DeepSeek Harness