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。
91 个项目，匹配「mod」
libinyam
Config-only DeepSeek Harness bundle for OpenAI-compatible vision models.
moduqishi
给纯文本大模型装上原生视觉：流式真实思考链 · 跨轮次无感重看 · 像素级证据与 SVG 图元 · OpenAI/Anthropic/Responses 三协议兼容 | Native vision for text-only LLMs: streaming real thinking chain, cross-turn re-view, pixel-level evidence & SVG primitives, OpenAI/Anthropic/Responses compatible.
secretxuan
Native-vision Windows computer-use for DeepSeek Harness: screenshots, UIA, OCR, and approval-gated input
shinjiyu
Vision sidecar for DeepSeek Harness: accept pasted images on text-only models.
wang-bool
DeepSeek Harness plugin for image upload, in-chat rendering, and vision analysis with cloud or local models. 图像上传、显示与解析。
wbb316
DSH（DeepSeek Harness）的本地 ComfyUI 图片生成插件：一个 generate_image 工具覆盖文生图 / 图生图 / 局部重绘 / 去背景，参数有智能默认值、报错可照做；零第三方运行时依赖，附 doctor 自检与 88 项测试（自带 mock ComfyUI，无需真装）。Local ComfyUI image plugin for DSH — one generate_image tool with text2img / img2img / inpaint / remove-background modes.
xuxun-oss
DeepSeek Harness all-in-one: no model switching — regular DeepSeek auto-routes to vision & image gen. Multi-backend: Gemini + any OpenAI-compatible (GPT-4o, Qwen-VL, GLM-4V, gpt-image, DALL-E, Flux, OpenRouter). gemini_vision/gemini_generate_image/gemini_optimize_image with vision self-check. Better than modlens.
DDDFXYqiming
Local OCR, color-statistics, pixel-scan, and metadata bridge for text-only DeepSeek Harness models; no external vision API.
GooDAnDReaDY
Universal vision bridge for DeepSeek Harness: attachments with native models, 40+ tools, PDF/OCR/diagrams.
InkshadeWoods
DeepSeek Harness 视觉增强插件：将图片交给外部视觉模型分析，输出带坐标化视觉原语的纯文本证据，使不支持多模态的文本模型也能在对话中理解图片、截图与文档。
aiyacharley
DSH plugin for DeepSeek Harness: 25 model tools spanning PubMed, Europe PMC, PubTator3 & Semantic Scholar — entity-aware search, cross-source unified search, metadata, full text, citations, MeSH & ID tools, citation counts & recommendations — plus a personal literature knowledge graph with an AI-powered PubTator3 concept layer.
cnChenKai
Tavily-backed WebSearchProvider for DeepSeek Harness (ctx.web) - keyless mode, no API key required
dongsheng123132
Native vision, gpt-image-2 and Seedance plugins for DeepSeek Harness via Xiapan Cloud
hyper-dsh-plugins
A lightweight DeepSeek Harness vision delegation tool for text-only routes, with native OpenAI Responses, Chat Completions, and Anthropic Messages adapters.
kk3ya03-star
Model-scoped DSH plugin: GPT Responses lifecycle, Native V2 compaction and Hosted/Alpha Search; Grok native Web/X Search
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。
nlqh7
给 DeepSeek Harness 纯文本模型加视觉：采用codex风格聊天框拖图自动分流给用户配置的视觉模型转文字，v4 不切换模型即可识图。 Vision for text-only DSH models: routes chat-box images to a user-configured vision model and returns text descriptions, deepseek-v4-pro reads images without switching.
qikairo7
多账号 Google Gemini 提供商（DSH 插件）：订阅额度即用即扣，账号池自动调度；主模型没有视觉也能贴图看图（池内 Gemini 自动转述），另有生图工具与中英双语设置页
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
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。
yakoylp
Convert Office documents and PDFs (incl. scanned, via CPU-first routing OCR with lightweight models: PP-DocLayout-L layout, RapidOCR text, SLANet tables, FormulaNet formulas) to structurally-formatted Markdown. CLI + dsh agent tool (md_convert).
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.
AlloyPlane
该仓库暂未提供项目说明。