视觉与多媒体

ysr666

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.

oil-oil

Near-native image understanding for DeepSeek Harness

HuanLinOTO

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

william-jin-cmu

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）

THU-MAIC

OpenMAIC for DeepSeek Harness: classrooms, slides, interactive widgets, and Socratic teaching

CraZY222123

未提供描述。

poiuyjie

DSH plugin: Auto-convert images to text for pure-text LLMs (DeepSeek etc.) via any vision model. No need to switch your main model.

TQSY114514

Appearance customization plugin for DeepSeek Harness: theme color palette, background image, opacity/blur, glass effect

JuneLearn

DeepSeek Harness Image2 生图插件，通过第三方 OpenAI Images 兼容接口调用 gpt-image-2，只需配置 baseURL 和 API Key。 | Image2 generation plugin for DeepSeek Harness via third-party OpenAI Images-compatible APIs.

Zhangbo-cn

Composer mic for DeepSeek Harness Web: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.

121103qwq

Hosted free vision sidecar for DeepSeek Harness with durable session evidence

MC5lan

给 DeepSeek 安装一双眼睛和一支画笔:会话里直接贴截图/图片,GLM 视觉模型先精确转写图片内容(报错信息、代码、界面逐字保留),然后 DeepSeek 继续处理你的问题——同一轮完成,全程无感;需要配图时,DeepSeek 自动调用文生图后端出图并显示在会话中。

kbpoyo

DSH 插件：让纯文本模型也能看图。Web 端直接粘贴图片即可发送，无需指定图片路径；模型自主调用视觉技能查看，多模态模型原生直通，零skill绑定。

1624318455

Edge TTS voice plugin for DeepSeek Harness: read assistant replies aloud, auto-read toggle, voice settings panel (free, no API key)

Agents365-ai

Image understanding for text-only models via OpenRouter free vision models

balcoz

DeepSeek Harness 本地 OCR 插件：粘贴图片，PP-OCRv5 + ONNX Runtime 识别文字，完全离线，支持 TUI 与 Web | Local OCR plugin for DeepSeek Harness — paste an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline. Supports TUI and Web.

Scorp1o117

Vision model for DeepSeek Harness | DeepSeek Harness 外置视觉模型插件

Sorwcyra

Paste images into DeepSeek Harness with a four-model vision race, OCR, and an automatic text bridge.

Favio8

DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.

PicGo

Upload images and files to your image host from DeepSeek Harness, powered by PicGo

Bald0Wang

DeepSeek Harness plugin: image_generate tool with qwen-image-3.0 (Aliyun MaaS) and doubao-seedream (Volcano Ark) providers

tsonglew

Audio/video preview viewer for dsh-better-sidebar: native playback with Range-seeking streaming route

3274375092

Voice input plugin for DeepSeek Harness: mic → local/browser speech recognition → text submitted as a normal chat message. Input-only and preset-agnostic.

caoyiwei850

DSH Web skin plugin with built-in themes and custom image skins

omdsh-dev

DSH Pet Corner: a floating pet, keyless pet-image proxy, favorites, and plugin-owned settings API

sliverp

DingTalk Stream text and image channel plugin for DeepSeek Harness

omdsh-dev

未提供描述。

omdsh-dev

DSH Typewriter: WebAudio typing ambience with a plugin-owned settings API and zero audio assets

omdsh-dev

未提供描述。

omdsh-dev

未提供描述。

ch1bug

Xiaomi MiMo search + multimodal tools for DeepSeek Harness agents: mimo_search/vision/audio/video/asr/tts

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

yangyue1974

Ambient soundtrack for DeepSeek Harness, driven by agent state. Streams 100k+ cleared tracks from AudioLib.ai — a track always finishes, so a state change never cuts one off.

dongsheng123132

Native vision, gpt-image-2 and Seedance plugins for DeepSeek Harness via Xiapan Cloud

Einskyle

DeepSeek vision bridge for dsh: route image attachments to a vision model (Qwen3-VL via pi-ai/llama.cpp) and continue on a text-only LLM (DeepSeek)

OoWJZZoO

A plug-and-play image-reading plugin for DeepSeek Harness. After installation, DSH will no longer refuse to feed images into sessions with pure-text models; instead, the image will be mapped as [Image #N] in the session. The Agent can then invoke tools on its own to read images from the session or from specified paths.

xiaoxianyu-office

DSH bundle plugin: chat-image bridge + read_image deny + conversational image_recognize for text-only main models | 纯文本主模型识图桥接与识图工具

ferstar

本地 OCR 插件：让纯文本生成 LLM 也能读懂图片 | Local OCR plugin: give text-only generative LLMs the ability to read images

sparkmio

SF视觉桥——给纯文本模型的 DeepSeek Harness 装上眼睛。

Zachary7456

DeepSeek Harness (dsh) 语音输入插件：麦克风按钮/快捷键录音，实时转写回填输入框。三种识别引擎：浏览器 Web Speech、本地 SenseVoice/Paraformer 离线后端（一键部署）、OpenAI 兼容云端 ASR API。

z827439974

Set the image as background for your dsh-webui

woyeshishen

未提供描述。

maple-pwn

Overleaf-style paper revision workbench powered by a DeepSeek Harness plugin (dsh-plugin)

BYYY-eng

DeepSeek Harness 文件上传与本地 OCR 插件 | File upload and local OCR plugin for PDF, Word, Excel, PowerPoint, images, and text files.

Xieweikang123

Give a text-only dsh model eyes: pasted images recognized into text via an OpenAI-compatible vision endpoint.

sjscy05

未提供描述。

pinch-eng

Dub video and audio into 10 languages with voice cloning, from a DeepSeek Harness agent | DSH 视频/音频配音插件

cesaryike

DSH 插件:让纯文本模型对话也能拖图/贴图——图片自动保存到会话工作区,以文件路径交给模型(多模态模型不受影响)

xiaoshihou514

DeepSeek Harness: vision

CharlesLiuZC

DeepSeek Harness with Voice Context speech-to-text integration

ddbj-hub

Persistent wallpaper skin for dsh web: static image or muted looping video background with translucent panels.

1HelloMan1

DeepSeek Harness usage dashboard with API balance, daily spend, external vision-call accounting, per-model stats, call logs, cache rate, TTFT, and CSV export.

superboy911

DSH model-routing plugin for keyword routing and isolated image generation / DSH 关键词路由与隔离生图插件

Fu3rte

Plug-in vision for text-only DeepSeek Harness (dsh) models: built-in free/cheap VLM presets + multi-image batch analysis

beijingwahw

dsh-conv-export（对话导出）— export the current DeepSeek Harness conversation as Markdown, PDF, or a long PNG image

CaoNing3212

自定义Deepseek Harness webUI主题

baconbao

A DeepSeek Harness Plugin for Previewing Mermaid Diagram by Images in Chat Sessions

kw78

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.

PiyotaHu

Local-first full-duplex voice for DeepSeek Harness, orchestrated by Muxiva

haiziyao

Vision routing and image generation for DeepSeek Harness through a fixed Mix model.