Bundle
dsh-mmx
MiniMax CLI bridge for DeepSeek Harness (dsh): mmx-backed web search fallback and transparent image understanding, with first-run onboarding and a settings card.
crazyma99
Browse
469 results
Bundle
dsh-codex-canvas
DeepSeek Harness tool plugin: image generation (gpt-image-2) via the Codex CLI, with inline Web preview
mindcarver
Bundle
dsh-image
图片处理：读取图片尺寸/格式、缩放与格式转换（内置 ffmpeg，跨平台）
uckkk
Bundle
dsh-disk-browser
DSH sidebar button to browse server disk folders (including hidden ones) with text and image preview.
yanJ26
Bundle
dsh-media-guard
Request image optimization, intelligent retention, and observability for DeepSeek Harness (DSH)
spyfree
Bundle
dsh-files-panel
Community DSH plugin: right-side workspace file tree, markdown preview, image preview, highlighted source. Does not patch DSH core.
aa2246740
Bundle
dsh-tool-accurate-vision
Model-facing accurate_vision tool: precise image spatial reasoning via a vision model
imkingjh999
Bundle
dsh-show-picture
DSH (DeepSeek Harness) Cordis plugin that lets the agent display images — local files or URLs — directly inside the conversation.
Yaing-Yan
Bundle
@dsh-external/dsh-image-gen
DSH 通用图像生成插件：接入任意 OpenAI 兼容生图网关（自定义 baseUrl + 模型 + API Key），设置页可视化配置。工具 dsh_image_gen / dsh_image_gen_config + 命令 /dsh-image-gen + skill。
hoyyang
Bundle
dsh-provider-pro
Custom provider enhancements: User-Agent override, reasoning-level switching, and image-input declaration for DSH custom providers · 自定义供应方增强：UA 覆盖、推理等级切换、图片输入声明。
Mortal520
Bundle
dsh-rembg
DSH rembg plugin with CPU/GPU background removal and setup UI
mengruoa
Bundle
xby-image-detect
检测图像中的80类COCO目标（人、车、动物、日常物品等），输出边界框、置信度和类别标签。
xby-skill
Bundle
kling-ai-deepseek-harness
Turn every idea into an image or video with Kling AI. In DeepSeek Harness, use natural language for text-to-image, image-to-image, text-to-video, image-to-video, reference-image creation, task tracking, and result previews.
Wlain
Bundle
xby-extract-image
MCP服务器提供从本地文件、URL提取图像并转换为base64格式的功能，适用于LLM分析。
xby-skill
Bundle
dsh-image-picker
DeepSeek Harness Web GUI 输入框 📎 选图按钮:通过系统文件选择器添加参考图,绕开拖拽环境问题,复用官方附件管线(缩略图/上限校验/随消息上传)。Image-picker button for the conversation composer.
liujia-io
Bundle
dsh-llm-multimodal
DSH 插件：提供文本 / 图像 / 视频 / 语音 / 音乐 五个生成工具，模型从 llm-pi-ai 自动发现，含 Settings UI (llm-multimodal namespace)。
xiaokaizhou
Bundle
@maiziman/dsh-model-capabilities
Automatic reasoning and image capability detection for custom DeepSeek Harness models
maiziman
Bundle
dsh-image-amnesia
Keep native vision, drop historical images before they hit relay providers. Global DeepSeek Harness bundle for every agent.
Choco-Zz
Bundle
dsh-vision-assist
DeepSeek Harness 视觉助手插件：给没有视觉能力的模型配一个可随时切换的多模态识别模型。输入框图片自动落盘并改写为文本提示，主模型调用 vision_recognize 工具即可完成看图；识别模型在 settings 的 vision-assist 命名空间热更新切换。
wjling
Bundle
dsh-skin-glass
Frosted-glass skin for the DeepSeek Harness web UI: pick any image as background, theme colors extracted from it, glassmorphism surfaces.
noexcs
Bundle
auto-vision
DSH（DeepSeek Harness）图片一体化插件：粘贴图片只进对话不进模型请求（llm/stream 清洗），并注册 see_image 工具让文本模型通过任意 OpenAI 兼容视觉 API 按需看图
h-k-c
Bundle
@uachar/dsh-vision-plugin
Vision recognition plugin for DeepSeek Harness: paste images into the composer, recognize them via GLM-4V on the host side, and inject the result into the conversation.
uAcharGG
Bundle
dsh-minimax-image
MiniMax 文生图插件：把一句话画面描述生成图片并保存到工作区，作为 `image-gen` 工具提供给模型调用。
Jack-sun-learner
Bundle
dsh-qwen-multimodal
DSH bundle: Qwen multimodal bridge — vision (qwen3-vl), speech-to-text (qwen3-asr), text-to-image (qwen-image), via the deepseek-vision skill scripts
wuwangmao