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。
142 个项目，匹配「im」
lhbsaa
DeepSeek Harness vision plugin: analyze_image (structured OCR evidence) + capture_image (USB camera visual loop). 摄像头视觉闭环 + 结构化证据，支持 Ollama / DeepSeek / Xiaomi 三后端。
loyalchiiina
DSH plugin: full-screen chat image lightbox (zoom/pan/download/page), conversation-wide thumbnail grid with adjustable columns, hide/show, jump-to-image, lossless native-resolution TIFF/HEIC display, copy local path & show in folder. 对话图片灯箱+缩略图网格+隐藏/跳图+TIFF原像素无损显示+复制路径/打开文件夹的 DSH 插件。
orchestral-media
TypeScript library for building multimedia-generation agents: text-to-image, video, speech and audio pipelines with capability-based model routing, automatic cross-model fallback, and BYOK direct provider calls (no gateway). 27 built-in patterns, provider-SDK-free core.
reimu-create
DSH plugin: text-only models (e.g. DeepSeek-V4) automatically see images via a vision model. Official surface-replace, cache-friendly, human transcript untouched. 纯文本模型自动识图桥
secretxuan
Native-vision Windows computer-use for DeepSeek Harness: screenshots, UIA, OCR, and approval-gated input
shaoqiuyuavailable
Scene-aware vision routing layer for DeepSeek Harness (dsh): decides which engine/backend an image should go to (chat/UI/table/code) before other vision plugins route it. Switch-gated, front-loaded, never touches other plugins' tools. 场景级识图路由层。
xiaoshi7915
DSH local knowledge base plugin: multi-format import, smart chunking, vector index, hybrid search (BM25 + sqlite-vec + RRF) for agent long-term memory
xiaoyuink
图片识别插件 for DeepSeek Harness：自动判断当前模型识图能力，支持多供应商视觉模型管理与检测
zclDragon
dsh plugin: generate_image tool for text-only models via the Antigravity CLI (Gemini image generation).
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.
Aidenwu0209
Unlimited-OCR for DeepSeek Harness with a native tool and GUI configuration
AlloyPlane
该仓库暂未提供项目说明。
Clearchenpro
DeepSeek Harness plugin: right-side whole-disk file browser with name/size/mtime sorting and drag-into-chat
CultOfLuna
DeepSeek 的"自动挡"：有图切 Vision，无图回 Pro/Flash，一键都不用点。 DeepSeek's "automatic transmission": image in → Vision, image out → back to Pro/Flash — not a single click.
GooDAnDReaDY
Real-time X (Twitter) search, author profiling, trends, and fact-checking tool suite powered by SuperGrok OAuth for DeepSeek Harness.
JuneLearn
DeepSeek Harness 多服务图片生成与编辑插件，支持 OpenAI Images、Gemini Interactions 与顺序故障转移。Multi-provider image generation and editing for DeepSeek Harness.
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).
Mappedinfo
DSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see images
SCT192221
DeepSeek harness多模态插件，接近原生体验。
Xieweikang123
Give a text-only dsh model eyes: pasted images recognized into text via an OpenAI-compatible vision endpoint.
dingchenhui0618-arch
Bundled imagegen skill for DeepSeek Harness: generate or edit raster images from the agent through any OpenAI-compatible GPT Image endpoint.
eclipti
A-share full-chain investment research plugin for DeepSeek Harness: real-time quote, Buffett-style value scoring, risk radar and institutional consensus in one tool
fengs2021
给 DSH 文本模型装眼睛：图片自动调用 mmx（MiniMax VLM）识别，识别结果注入模型上下文
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。