dsh-vision-complete
Yts1919
给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件:看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读,一键安装(DSH 插件)。
GITHUB TOPIC
18 个项目包含此标签
18 个项目
GitHub Topic 精确匹配
Yts1919
给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件:看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读,一键安装(DSH 插件)。
Flyvhidbwo
DeepSeek Harness 插件:DeepSeek Pro 大脑 + 自动识图。GUI 附加图片默认经官方 deepseek-v4-flash-vision-exp 原生识图,转译成文字后交给 DeepSeek 作答(纯文本的 V4-Pro 也能看图);支持百炼/智谱/OpenRouter 等任意 OpenAI 兼容 VLM,无 key 自动探测本地 Ollama;安装时有一问式确认
为DSH接入本地大模型能力:在「设置→插件」页一键启停本地 llama.cpp 大模型(双槽x双模态x双预设),卡片内配置、一条命令安装、自动注册,装完即用| Enable local large model capabilities for DSH: One-click start/stop for local llama.cpp models (dual‑slot × dual‑modal × dual‑preset) right in Settings → Plugins; configure within the card, install with a single command, automatically register, and ready to use
Harvey-Will
DeepSeek Harness 图像理解插件 · 8 种分析模式 · 支持任意API接口 · 内置免费视觉模型 | DeepSeek Harness vision plugin · 8 analysis modes · works with any OpenAI- or Anthropic-compatible API · built-in free vision model
TaylorSwitiger
DeepSeek Harness (dsh) plugin: one local bridge for ChatGPT Codex / Claude / ZCode (GLM) / Qwen subscription plans — settings status card, one-click provisioning, zero core changes. npm: @taylorswitiger/dsh-plan-bridge
nickhelion
Secure DeepSeek Harness plugin monorepo: Qwen Token Plan Responses provider and ServerChan notifications
ShuiHan268
DeepSeek Harness 的 Qwen-MM-Plugins 集成插件:12 个多模态 MCP 工具(视觉/OCR/定位/ASR/音视频)、Web 设置页(粘贴 Qwen API Key 即用)、内置技能与一键安装器
pricklywiggles
Loop guard for DeepSeek Harness: denies repeated identical tool calls and caps per-agent calls, outside the model where instructions cannot reach
782042369
DSH (DeepSeek Harness) compatibility guard plugin: fixes reasoning-model compaction truncation, doomed sandbox-escalation fail-close, and missing tool description for GPT/Qwen/third-party models
zjcdkj
DeepSeek Harness (DSH) plugins. qwen-image gives a text-only coding model eyes: an image goes to a Qwen-VL route through ctx.llm and comes back as text, so DeepSeek keeps coding while Qwen looks. Pure ESM, no build permission at install. | DSH 插件集:qwen-image 让纯文本模型借千问 VL 读图,返回文本;纯 ESM,安装无需构建授权。
Leeminjing
Give text-only DeepSeek models on-demand vision: upload images, DeepSeek answers by calling a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).
RRRosmontis
Qwen-MM-Plugins integration bundle for DeepSeek Harness (dsh) — multimodal MCP tools (vision, OCR, ASR, search, video, Blender, FreeCAD) + image attachment bridge. 让 DeepSeek Harness 原生支持多模态。
SnowRikka
DeepSeek Harness plugin: run subagents on a local llama.cpp model via the OpenAI Responses (/v1/responses) protocol — LLM adapter + delegation skill
zfu691531-hash
Lightweight realtime ASR → DeepSeek Harness → TTS community plugin.
Andy294753951
DeepSeek Harness plugin: drive a logged-in Qwen web session (Qwen3.8 on qianwen.com / qwen.ai) through a local browser bridge
Golopuer
When you use DeepSeek harness,you may hate that the big fish is always thinking in English,not Chinese(or the other language).Dot't worry,Deepseek has written an Plugin to translate it,but with qwen 3.5 0.8B's help......This Plugin will translate thinking without API.It is helped by deepseek V4 pro.
umicorn07
Qwen / DashScope Token Plan web search provider plugin for DeepSeek Harness (dsh)
wuwangmao
DSH bundle: Qwen multimodal bridge — vision (qwen3-vl), speech-to-text (qwen3-asr), text-to-image (qwen-image), for DeepSeek Harness