dsh-multimodal
MC5lan
给 DeepSeek 安装一双眼睛和一支画笔:会话里直接贴截图/图片,GLM 视觉模型先精确转写图片内容(报错信息、代码、界面逐字保留),然后 DeepSeek 继续处理你的问题——同一轮完成,全程无感;需要配图时,DeepSeek 自动调用文生图后端出图并显示在会话中。
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。
98 个项目,匹配「ai」
MC5lan
给 DeepSeek 安装一双眼睛和一支画笔:会话里直接贴截图/图片,GLM 视觉模型先精确转写图片内容(报错信息、代码、界面逐字保留),然后 DeepSeek 继续处理你的问题——同一轮完成,全程无感;需要配图时,DeepSeek 自动调用文生图后端出图并显示在会话中。
Aidenwu0209
PaddleOCR skills for DeepSeek Harness with native tools and GUI configuration
DoloresCaritasAngelus
Auxiliary model system for DeepSeek Harness: unified aux-LLM routing (per-task model, timeout, concurrency, failure cooldown, main-model fallback) + vision_analyze / web_extract / compress_text tools, settings page, and session image lifecycle cleanup.
Letter2025
Tool search & slimming for DeepSeek Harness: Hermes-style progressive disclosure — search, describe, and call long-tail tools on demand
dongsheng123132
Content-addressed artifact, fact, action and report lineage for DeepSeek Harness
libinyam
Config-only DeepSeek Harness bundle for OpenAI-compatible vision models.
A3Boy
Multi-provider Web Search & Fetch for DeepSeek Harness — Tavily, Exa, Firecrawl, Brave, You.com, Jina & SearXNG with fallback and native settings UI.
Argonaut790
Image understanding, OCR, and persistent visual evidence for text-only DeepSeek Harness models
Fisfzy
面向 Zotero 论文库的浪潮式 RAG 细节检索系统 —— DSH 外部插件。移植 VCPToolBox 浪潮语义动力学思想(标签河道图传播/虫洞跳转/钟型阻尼/Ω重排),配 BM25+RRF 混合检索、claim-evidence 忠实度校验、两级增量索引
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
cnChenKai
Brave Search-backed WebSearchProvider for DeepSeek Harness (ctx.web)
hancao97
Local-first A-share research workbench for DeepSeek Harness: market dashboards, watchlists, valuation, four investor agents, versioned reports, and continuous post-report chat.
ihuajiu
Natural-language plugin search for DeepSeek Harness — ask what you need, get matching dsh.so plugins with install commands.
moduqishi
给纯文本大模型装上原生视觉:流式真实思考链 · 跨轮次无感重看 · 像素级证据与 SVG 图元 · OpenAI/Anthropic/Responses 三协议兼容 | Native vision for text-only LLMs: streaming real thinking chain, cross-turn re-view, pixel-level evidence & SVG primitives, OpenAI/Anthropic/Responses compatible.
omdsh-dev
DSH JSON Schema 验证工具插件:validate/paths/explain/normalize,零网络零动态执行
welsione
一个工具 = MiniMax 全部多模态能力:DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover/search/quota) for DeepSeek Harness (DSH)
wly8691-jpg
KnowLP-RAG: dual knowledge-graph RAG for Markdown notes — dsh plugin add @eqman00003/knowlp-rag · MCP + native Cordis plugin for DeepSeek Harness (dsh) & Claude Code
zouyuanqing
Native interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid / zoom / annotate / measure / diff / color / OCR) + MiMo V2.5 multimodal backend, zero external MCP servers.
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.
83079Vermont
A self-contained DeepSeek Harness (DSH) plugin that registers a global model tool parse_docs: parse local PDF / DOCX / PPTX / XLSX / TIFF and image batches into Markdown with local MinerU.
Bernardxu123
DeepSeek Harness (dsh) 官方 bundle 规范插件集合: dsh-vision 看图 + dsh-sensenova-image 生图 + dsh-client-stats-decimal 统计两位小数
GXX182
DeepSeek Harness plugin that bridges session images to pluggable vision APIs while keeping DeepSeek as the primary model.
Hyp6666
A lightweight DeepSeek Harness vision delegation tool for text-only routes, with native OpenAI Responses, Chat Completions, and Anthropic Messages adapters.
LeslieWylie
Render Markdown to standalone, self-contained HTML in the DeepSeek Harness — an md_html_render tool that works headless, plus a preview/export drawer in the web GUI. One renderer behind both. Zero dependencies.