Modlens
Turn images into structured evidence for text-only models, with OCR, layout, and semantic understanding.
DSH vision plugins add image understanding, OCR, visual grounding, screenshot analysis, and multimodal workflows to DeepSeek Harness. They are how a text-only model reads an interface, a diagram, or a screenshot.
Turn images into structured evidence for text-only models, with OCR, layout, and semantic understanding.
Native image Q&A, long-screenshot OCR, interface restoration, grounding, and pixel comparison.
Route image turns to a vision model with a free fallback chain and pixel-level tools, without Python.
Repositories with traceable evidence of a DeepSeek Harness relationship. They have not been reviewed, install tested, or security checked — the signal below each one is the whole of what the registry currently knows.
A visual, non-linear conversation workspace plugin for DeepSeek Harness ; A canvas-based session explorer and branching workspace for DeepSeek Harness.
DeepSeek Harness (DSH) plugin: a live iOS Simulator — and a USB-connected iPhone — inside the conversation. 22 agent tools for booting, building, driving the UI by accessibility identity, OCR text or list rows, plus a streaming sidebar panel you can tap and drag on.
开源版锤子便签,复刻锤科美学,一键Docker私有化部署,支持skill调用,支持dsh plugin,支持多租户,一键生成公众号格式,支持导出便签为图片
DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.
DSH (DeepSeek Harness) Web GUI AI image generation plugin: text-to-image & image-to-image via OpenAI-compatible endpoints (gpt-image-2), with shared cross-device history.
Visual conversation map for DeepSeek Harness — sessions as cards on a whiteboard: drag to arrange, double-click to chat, draw an edge to fork with injected context. ADHD-friendly spatial memory. · DSH 可视化对话地图
Near-native image understanding for DeepSeek Harness
VCP visual-synesthesia plugin v2 for DeepSeek Harness (official Slot API): raw-HTML vcp-root cards, streaming render, KaTeX/Mermaid/SVG, builtin fonts
向模型暴露 MinerU 文档解析工具,将 PDF/图片/DOCX/PPTX/XLSX 转为结构化 Markdown/JSON | Exposes MinerU document-parsing tools to the model, converting PDF/images/DOCX/PPTX/XLSX into structured Markdown/JSON
Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the benchmark behind that judgement — four fixtures, 23 injected defects, and every raw model transcript. Retires itself when DeepSeek ships vision.
DSH 对话分享插件,分享单轮或多轮对话,可导出为图片或 Markdown。Share DSH Q&As or selected conversation groups as PNG or Markdown.
DirectorX as a DeepSeek Harness plugin: AI video/image/audio skills, knowledge corpus, and configurable vision/image/video/audio model tools.
dsh 插件:给纯文本 DeepSeek 加视觉——view_image 工具桥接任意 OpenAI 兼容 VLM(默认智谱免费档,实测 4 厂商 10 模型)
Visual AI workflow orchestrator for DeepSeek Harness (dsh): multi-agent DAGs, live execution, recovery, and Feishu integration.
A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model catalog from one wallet, paid per request over x402.
DSH 网页界面换背景:侧栏「壁纸」按钮弹出右侧抽屉,支持系统预设/纯色/渐变/图片/视频,滚轮+拖动小图同时管缩放与定位,毛玻璃质感,本地媒体伺服不走云端。DSH web background & wallpaper plugin with drawer UI, glassmorphism and local media serving.
使用 DeepSeek 官方多模态视觉模型让你的 Agent 不再眼瞎(支持 DSH、Zed、OpenCode、Codex、Claude Code、Cursor、Claude Desktop)
Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel
Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek Harness 全本地文档智能插件,支持 PDF、Office、图片与离线 OCR
DeepSeek Harness 插件:DeepSeek Pro 大脑 + 自动识图。GUI 附加图片默认经官方 deepseek-v4-flash-vision-exp 原生识图,转译成文字后交给 DeepSeek 作答(纯文本的 V4-Pro 也能看图);支持百炼/智谱/OpenRouter 等任意 OpenAI 兼容 VLM,无 key 自动探测本地 Ollama;安装时有一问式确认
DeepSeek Harness (DSH) 的 Galgame 生成器:提供一份剧本文档 + 立绘/背景/音乐素材,即可生成一个可玩的视觉小说(Galgame)网页。 新增一个GalGame生成模式,在这个模式的工作区下提供一份剧本文档 + 立绘/CG/背景/音乐素材等,即可生成Galgame网页。
DSH plugin: Auto-convert images to text for pure-text LLMs (DeepSeek etc.) via any vision model. No need to switch your main model.
DSH 插件:大图切 800×800 无损小块 + 坐标标注 + 分块聚合逻辑,直连 deepseek-v4-flash-vision-exp 识别;仅用纯官方 DSH 功能,零依赖第三方插件,不统计 token/费用。
Visual browser element annotation for DeepSeek Harness, capturing DOM, styles, accessibility data, comments, and viewport screenshots. DeepSeek Harness 浏览器元素标注插件,捕获 DOM、样式、可访问性数据、评论和视口截图。
Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes. DeepSeek Harness 辅助模型插件:为视觉理解、上下文压缩、审批审查、子代理、会话标题与图片生成提供独立的模型路由、工具与系统提示,全程不触碰主对话模型。
One upload button plus drag-and-drop files into the conversation as local paths: save to project uploads/, path text into the input box, works with any vision tool
DSH 插件:图片与文件直达纯文本模型——图片保留原生附件体验,PDF/Office/压缩包/视频/音频显示为附件栏方块,点击发送时自动转为工作区路径,配合 dsh-vision-toolkit 粘贴即看图。A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep the native attachment UI, other files show as square chips in the rail, paths append on send — pairs with dsh-vision-toolkit.
Vision-language gateway plugin for DeepSeek Harness - paste an image, DeepSeek sees text
dsh + ModLens 视觉能力一键安装包:给 DeepSeek Harness 装上看图能力(Windows EXE 安装器 + 智谱 GLM-4V-Flash 免费视觉引擎)
为 DeepSeek Harness 增加外挂识图模型:圆形鲸鱼按钮、发送图片识图自动回传、模型自主截图+识图工具、多协议自动适配、小白一键安装(未装 Node.js 自动下载)
为DSH(DeepSeek Harness)量身打造的视觉插件,现已支持agent调用图片显示/Vision plugin for DSH(DeepSeek Harness),support Proactive Image Display.
用于展示对话中读取的图片(read_image 结果):DSH Web GUI 对话流专用 Read image 行,默认缩略图 + 页面内全精度放大层(缩放按钮/滚轮/1:1)· Displays images read in the conversation (read_image results) in the DSH Web GUI
Vision model for DeepSeek Harness | DeepSeek Harness 外置视觉模型插件
专供 deepseek-v4-flash-vision-exp 的高清识图增强插件:放宽 DSH 图片限制 + highres_read 分块识图工具。
Sticky notes for DeepSeek Harness: draggable notes with text & image support, 9 skins, and AI-powered read/write. DeepSeek Harness 便签插件:可拖拽,支持文字与图片、9 款皮肤,AI 可读写。
Media generation and visual understanding for DeepSeek Harness, with multi-provider routing and the integrated Iris workbench.
Vision for DeepSeek Harness: Doubao Web by default (zero-cost, no API key), Antigravity IDE quota (flash/pro), any IDE CLI, Gemini — auto detail escalation, evidence memory
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness — strict evidence, health-checked failover, original pixels, and Token accounting.
DSH 极简模式视觉辅助:保持灰测体验所需的首轮干净上下文,同时通过隐藏上下文和按需 Bash 工作流提供视觉分析 | Vision assistance for DSH minimal mode: preserve the clean first-turn context behind the gray-test DeepSeek experience while adding on-demand visual analysis through a hidden-context Bash workflow.
Model-agnostic Computer Use for DeepSeek Harness: isolated browser, Windows native helper, third-party vision perception, and a Chrome Cookie Bridge.
AI 写简历容易,但写完总会遇到模板难看、排版溢出、页面留白、改一处全局变形等问题。dsh-resume 专注解决“内容生成后的视觉复核”:让 AI 和用户一起把简历调到真正适合投递的刚好一页。AI can write a resume, but the result often looks unbalanced, overflows the page, leaves large blank areas, or breaks after a small edit. dsh-resume focuses on visual review after generation, helping AI and users refine the resume into a polished.
DeepSeek Harness plugin. 支持直接把图片、文件等拖入到dsh中。更方便地拖拽;image & file drop.
基于 MinerU 的 DeepSeek Harness 多模态文档解析插件:PDF/Word/PPT/Excel/HTML/图片 → 结构化 Markdown(免 Token 的 Agent 轻量解析 / 精准解析双 API 模式)
On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
DeepSeek Harness(DSH)网页界面可自定义品牌区域——用您自己的本地图片替换鲸鱼标志和 DeepSeek 字标,并编辑 HARNESS 徽章文字。
Image generation & visual processing suite for DeepSeek Harness: pluggable providers (FAL, Replicate, OpenAI, ChatGPT Plus, Grok, ComfyUI, SeaDream, Gemini), tools (remove_background, upscale_image, vectorize_image, blend_images), style presets and chat card.
Guide Dog for DSH — MiniMax multimodal plugin: image/video/music/speech generation & vision tools, voice mode, voice input. Real-time call mode implemented: streaming voice conversation, unified floating UI, adaptive prompts, zh/en i18n. Accessibility features planned for testing & rollout. Featured in the dsh-recommend plugin registry.
DeepSeek Harness 生态的 GitHub 可视化登录工具(零终端):设备码流程,令牌同步 gh CLI | Visual GitHub login for the DSH ecosystem - no terminal needed
DeepSeek Harness plugin: describe_image — give a text-only model vision through an OpenAI-compatible VLM endpoint
DSH 模型代理插件:按模型粒度走代理(Clash 等)+ 失败自动重试 + 多模态模型镜像 + 逐模型测试连接,模型列表与官方同步,设置页实时生效。
为纯文本模型按需识图:DSH 零补丁 Cordis 插件(prism_see 工具 + 图片 VEP 降级 + 技能运行时注册)+ Codex Skill;多 Provider 视觉 API,VEP/1 低 Token 视觉证据包
DSH 轻量截图插件:轻 : 纯 PowerShell 实现,零依赖、零二进制;截图能力独立维护,不随任何上游更新而失效。 摆 :一键全屏即拍;框选前整个桌面保持可操作,所有窗口像布置画面一样自由移动、缩放;鼠标悬停任意窗口即亮起吸附边框,点一下直接截该窗口,被遮挡也能拿到完整内容,所得即所见。 自助:Agent 可随时自行截屏;接上 modlens(选装),截屏 + 识图一步产出结构化内容(OCR/版面/语义),纯文本模型也能消费。
DeepSeek Harness 本地 OCR 插件:粘贴图片,PP-OCRv5 + ONNX Runtime 识别文字,完全离线 | Local OCR plugin for DeepSeek Harness — paste an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline.
Hosted free vision sidecar for DeepSeek Harness with durable session evidence
DeepSeek Harness EAC 视觉全家桶:15 个像素级视觉工具(增强版 dsh-tool-vision)+ 桥接内联预览 + 拖拽文件上传,单端点驱动,对话干净,EAC 原生设置适配
Full-coverage image tiling for DeepSeek Harness vision models, dense-text OCR, and document AI
DeepSeek Harness 多模型路由插件:让专业的事情交给专业的 agent——自定义视觉/翻译/语音/子代理等专业 agent 并绑定独立模型,多模态账号一键登录、账号池健康路由与实时用量统计
DeepSeek Harness 插件:让 deepseek-v4-flash 等不能看图的模型也能处理聊天图片,内置识图工具。安装:dsh plugin --profile web add dsh-image-pathify
Galgame / visual-novel UI plugin for the DeepSeek Harness: a whale-girl companion with animated expressions, scene-at-a-time dialogue, and an LLM emotion judge
DeepSeek Harness plugin for content-aware PDF reading by vision models