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。
200 个项目，匹配「image」
NormanFxxkingRockwell
DeepSeek Harness 视觉桥：自动发现你已配置的多模态模型，给纯文本主模型装上 vision 工具，识别结果以纯文本返回。零配置，一条命令安装。
PangYiMing
DSH plugin: pixel-diff two screenshots into diff.png + triptych (pixelmatch) — 像素对比工具
SamurAIGPT
DeepSeek Harness plugin exposing MuApi's 100+ image/video/audio generation models as an agent tool
Xin-Zhang-IceMan
DeepSeek Harness 视觉插件：让纯文本模型拥有视觉能力 / Vision plugin for DSH: vision_analyze tool + automatic image transcription for text-only models.
YZz-S
DeepSeek Harness (dsh) vision plugin — a fork of ModLens adding multi-engine image reading (Gemini, Volcengine Ark/Doubao, Claude) with per-call engine selection.
ZhuXinAI
CLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.
alanzhao0128
Multimodal plugin for DeepSeek Harness (dsh): understand images and generate images via configurable OpenAI-compatible or DashScope endpoints.
alcohol-101
Custom background (image / GIF / animated wallpaper) plugin for the DeepSeek Harness (DSH) Web GUI - enable switch plus a local asset library, with separate display mechanisms for the official theme and skin-center skins.
cking000bigdemon
Eight DeepSeek Harness plugins: persona, language guard, per-request vision fallback, python/windows write guards, cross-agent memory, image generation, and skill shell injection.
cransmathenia666-hash
Give text-only DeepSeek Harness (dsh) agents vision — pasted images auto-convert to text descriptions with persistent caching, each image converted only once.
fryghost
Community plugin for DeepSeek Harness: give text-only models eyes - paste images natively, described via an OpenAI-compatible vision API
gmleong
Give text-only models eyes: analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible endpoint. 给纯文本模型装上眼睛的 dsh 插件。
hZsFN
QQ official bot private message (C2C) bridge for DeepSeek Harness (dsh): per-user persistent agent sessions, image attachments, auto-reconnect
haozhu11
Background image plugin for the DeepSeek Harness web UI (dsh web): upload local images as the whole-UI background, with a theme-aware readability matte, WebP-first compression and IndexedDB persistence.
hawkongz
让纯文本模型通过桌面豆包看见聊天图片的 DeepSeek Harness 宿主插件(CDP 桥接,全预设生效,识别可取消)
jeffi369
Give DeepSeek Eyes · 给 DeepSeek 装眼睛 — a DeepSeek Harness (DSH) Skill: local vision models or vision APIs let DeepSeek read images and graphic files
让 dsh 通过 grok2api 的 API 获得图片与视频生成能力（generate_image / generate_video）。
marlonLau
One-click DSH background switcher backed by local Wallpaper Engine images/videos
me9rez
DeepSeek Harness (dsh) bundle plugin: vision_analyze tool lets text-only LLM agents read images via SenseNova VLM, with Schemastery config and single-source credentials
moton16
Give your text-only LLM eyes: zero-dependency MCP server that reads images via external OpenAI-compatible vision models with automatic provider fallback, plus a one-command patch for DSH image-attachment degradation.
nexsjournal
Includes image recognition and generation functions.
nexsjournal
给 DeepSeek Harness（DSH）加上第三方生图/改图能力的插件：对话召唤 + 设置卡片，支持 OpenAI 兼容 / 阿里百炼 / Replicate / fal.ai
princefrogdida-ux
Windows-first vision suite with image understanding, OCR, screenshot diffing, and multi-provider routing for DeepSeek Harness.
ropon
One-key ClawRouters plugin for DeepSeek Harness: chat, image, video, and web search
