Reading images, screenshots, PDFs and OCR — visual understanding.
Active this week · L5 run-tested · low risk · most starred
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
让 AI 实时看见你的屏幕：按变化量筛选帧、多帧拼进一张图，静止画面几乎不花 token
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.
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.
1511 verified plugins belong to this category. Filter from the sidebar, search, and paginate.
1,511 artifacts · sorted by
Every entry verified via GitHub API · automated security scans · sandbox install testing, not manual review
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
dsh plugin --profile web add @liustack/modlens
可在对话内生成、编辑、对比图像；内置 500 + 提示词、图库、多模型工作流，支持 ComfyUI。AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.
dsh plugin --profile web add dsh-image-gen@0.11.2Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
dsh plugin --profile web add dsh-vision-router@3.2.1让 AI 实时看见你的屏幕：按变化量筛选帧、多帧拼进一张图，静止画面几乎不花 token
dsh plugin --profile web add dsh-see-now@0.2.2DeepSeek 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.
dsh plugin --profile web add @zseven-w/dsh-ios@0.1.0-rc.12DeepSeek 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 plugin --profile web add @zseven-w/dsh-crew
DeepSeek Harness 的桌面自动化：给整台 Windows 机器装上眼睛和手。可以做人能做的任何事，包括且不仅限于CAD，WPS，浏览器操作，发微信。安全，快速，可靠，聪明，人性化。
dsh plugin --profile web add @momasiku/dsh-pilotDSH (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.
dsh plugin --profile web add @dickpy/dsh-imagegen@1.17.0
Use openai-codex models and image generation via ChatGPT OAuth for DeepSeek Harness.
dsh plugin --profile web add dsh-codex-connect
DSH 插件：在对话里调用本机 ComfyUI，用千问 Qwen-Image 2.1 出图。纯本地、不出网、不需要 API Key。
dsh plugin --profile web add github:wonderandyou/dsh-qwen-paint#v0.1.2
Cross-platform Computer Use plugin for DeepSeek Harness: observable desktop automation with an isolated virtual cursor, AX/UIA observation, screenshot vision, and 12 guarded tools.
dsh plugin --profile web add dsh-computer-use
DSH插件，将微信私聊消息桥接到DSH，支持文本、图片、文件、音视频的双向传输。目标是在微信端还原DSH的原生体验
dsh plugin --profile web add dsh-wechat@0.16.2
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
dsh plugin --profile web add github:HuanLinOTO/dsh-plugin-mineru
Model-facing Office tools for DeepSeek Harness: Word (.docx), Excel (.xlsx), and PowerPoint (.pptx) create/read/update with workspace-safe paths and PPT image embedding.
dsh plugin --profile web add dsh-office-tools@1.0.8
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 plugin --profile web add dsh-design-qa
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.
dsh plugin --profile web add dsh-share@0.5.0陪看：和智能体一起看视频 —— 跟着真实播放位置，每段结束前把分镜画面 + 带秒台词交过去；悬浮窗里能出声，也听得见房间。A DSH plugin that watches a video together, in sync with the real playback: a storyboard image + subtitle lines per segment, spoken replies and live room audio.
dsh plugin --profile web add dsh-watch-together@0.3.3
DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.
dsh plugin --profile web add picturereader@3.3.3