dsh-vision-linkLightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sprainJinyu/dsh-vision-linkDiscover The Best DSH plugins
Vision tools · DeepSeek Harness plugins — Page 58
1470results
Find image understanding, screenshot analysis and visual interaction plugins; compare inputs and usage.
dsh-vision-localLocal-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics / visual / uncertainty).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gloryxpnv/dsh-tool-visiondsh-vision-no-visionGives a text-only LLM vision capability
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wdwind/dsh-vision-no-visiondsh-vision-patchPer-model and per-route image-input (vision) checkboxes on the Models page's custom-provider cards, writing through the llm-pi-ai settings namespace.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ryasrk/dsh-vision-patchdsh-vision-plugin为 DeepSeek Harness 提供外部视觉模型能力：纯文本主模型通过 describe_image 工具调用外部视觉模型看图，拿到纯文字描述（多模态补全）。
dsh-vision-pluginDeepSeek Harness plugin: upload/paste images in the chat box; on send, transcribe via a vision model (dashscope) or offline Windows OCR, then inject the description into the message as 【解析了提供图片，图片内容是<描述>】.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zcma11/dsh-vision-plugindsh-vision-pro-bridgeGive text-only DeepSeek-V4-Pro real vision with zero new dependencies and DeepSeek-only routing: images are described by deepseek-v4-flash-vision-exp (your existing DEEPSEEK_API_KEY), then the text is handed to V4-Pro.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ShaineDemo/dsh-vision-pro-bridgedsh-vision-proxyGive a text-only DeepSeek Harness model eyes: a proxy provider that delegates image understanding to any vision-capable model the harness can route, plus vision and vision_config tools.
dsh-vision-recognizerDeepSeek Harness image recognition plugin: keep DeepSeek as the conversation brain while a configurable vision model (15+ providers, OpenAI-compatible + Anthropic) transcribes attached images. Configurable from Settings → Plugins.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kaixinbaba/dsh-vision-recognizerdsh-vision-resident常驻视觉服务：直连视觉模型（默认 opencode-go/minimax-m3，回退 zai-coding-cn/glm-4.6v）。describe_image / subagent_vision 工具 + 粘贴图片自动转译（llm/stream 钩子）+ 输入框视觉状态小胶囊与详情页（活动日志：指令/思考过程/输出）。零子代理、零 agent 上下文开销，按会话记忆窗支持视觉追问与验收。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AnnanRen/dsh-vision-residentdsh-vision-router-inlineDisplay companion for dsh-vision-router: keep Auto Vision routing, and put a square picture button on each original model row. Does nothing unless dsh-vision-router is installed.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MitsukiJoe/dsh-vision-router-inlinedsh-vision-skill让 DSH 里任何模型（包括 DeepSeek 这类纯文本模型）都能识别图片：识图技能 + 图片发送补丁，装上即用。
dsh-vision-subagentVision for text-only DeepSeek Harness agents: delegate image reading to a one-shot subagent on a configurable vision route (MiniMax / Kimi / any OpenAI-compatible provider), keeping image bytes and the vision model's context out of the main session.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ruby1304/dsh-vision-subagentdsh-vision-tilerLoss-aware, full-coverage image tiling for DeepSeek Harness vision models
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zyh20041227/improved_vision_for_deepseekdsh-vision-toggleDSH 模型视觉开关：设置页「模型视觉」行，为 llm-pi-ai 自定义路由下手写声明的模型切换 input 视觉模态（settings.mutate 官方通道，热生效）。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:123twtd/dsh-vision-toggledsh-vision-workbenchWindows-first vision suite for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:princefrogdida-ux/dsh-vision-suitedsh-vision-workbenchWindows-first, non-invasive vision tools for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:princefrogdida-ux/dsh-vision-workbenchdsh-visionplusDeepSeek VisionPlus — official-grade vision extension for DeepSeek Harness. Routes image understanding to a free vision-model pool (Zhipu GLM, SiliconFlow Qwen) with automatic fallback, rate limiting, one-click platform tests and live status lines; text stays on DeepSeek. One-command install. MIT.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qq247505/DeepSeek-VisionPlusdsh-visual-acceptanceLocal-first visual acceptance and regression workbench for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PolinniZhong/dsh-visual-acceptancedsh-visual-hierarchy视觉层级构建参考
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-visual-hierarchydsh-vlm-bridgeDeepSeek Harness (dsh) bundle plugin: vision_analyze tool lets text-only LLM agents read images via SenseNova VLM, with Schemastery config and single-source credentials
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:me9rez/dsh-vlm-bridgedsh-voice
★ 0dsh-voiceVoice for DeepSeek Harness — give text-only DeepSeek ears and a mouth: browser-native speech input (STT) + read-aloud (TTS), plus Whisper/TTS agent tools.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhuiyueya/dsh-voicedsh-voice-mimoVoice for DeepSeek Harness backed by Xiaomi MiMo: browser-native 🎤/🔊 UI (MiMo TTS read-aloud) + voice_transcribe/voice_speak calling MiMo ASR/TTS directly, with a configurable voice map and in-conversation speech strips. Fork of zhuiyueya/dsh-voice (MIT).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ch1bug/dsh-voice-mimodsh-wallpaperSet a custom background wallpaper for the DeepSeek Harness desktop app — presets, image URL, upload, and an opacity slider
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:keke050/dsh-wallpaperFind the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
Check and install
Review compatibility, dependency ranges and instructions, then copy the available install command.
Questions about DSH Hub
What is DSH Hub?
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
Does inclusion mean a plugin is tested and compatible?
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
How do I install a plugin?
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.