Vision & Multimodal

#1·modlens

liustack

3.4k

An official plugin that

#2·dsh-vision-router

ysr666

896

Add visual capabilities

#3·dsh-vision-toolkit

Anionex

783

Give vision to plain text models in DSH: paste images for Q&A, element localization, long-image OCR, UI reconstruction, and pixel comparison.

#4·graph-memory

adoresever

562

Provides a local SQLite knowledge

#5·dsh-image-gen

shanliuling

100

Adds in-conversation image generation to DeepSeek Harness web client, supporting Google Gemini, OpenAI, and ByteDance Seedream, with a built-in local image gallery.

#6·dsh-vision

oil-oil

79

Adds vision capability to DeepSeek Harness text

#7·picturereader

jing-hy

31

Adds visual document reading capability to the text-only DeepSeek Harness model: visual twin receives native thumbnails, local pixel tool with three-mode routing and optional external vision endpoint, image data can remain entirely local.

#8·deepseek-visionary/packages/dsh-plugin

xlight

13

Provides DeepSeek Harness with DeepSeek web visual model native tools (image recognition/OCR/login) and text model image bridging, no API Key required.

#9·dsh-vision-opencode

poiuyjie

13

Add a configurable image recognition model to DSH's text-only main model: automatically convert images sent in chat to text, while keeping the original multimodal model unchanged.

#10·dsh-vision

linenxi-ctrl

12

Integrates a third-party image recognition model into DeepSeek Harness: the configuration panel in the webpage's bottom-right corner automatically recognizes sent images and returns results to the model, while also enabling the model to capture and recognize screenshots.

#11·dsh-vision-proxy

Flyvhidbwo

12

Enable DeepSeek Harness to send images with DeepSeek models by automatically invoking a third-party vision model to transcribe images into text before passing to DeepSeek for answering.

#12·dsh-imagegen

dickpy

8

Add AI image generation sidebar to DSH Web GUI, with OpenAI-compatible API proxy, supporting text-to-image, image-to-image, and a history/prompt template library.

#13·dsh-deepseek-vision

siegfly

7

Adds sticker support to text-only DeepSeek: registers a visual routing mechanism where images are first described as text by a VL model, then passed to DeepSeek—no model changes or official modifications required.

#14·dsh-vision

54xkeee

7

Adds visual capabilities to plain-text DeepSeek: defaults to Doubao Web free channel, supports automatic fallback across multiple channels, and enables structured evidence memory reuse across conversation turns.

#15·dsh-free-vision

FuzzySoul

6

Add image understanding to plain text DSH models: register the image_understand tool to call free vision APIs (Qwen/Doubao/Silicon), and include built-in show_image to render images inline in the conversation flow.

#16·dsh-minimal-vision

Flora233333

6

Add visual capabilities on demand in DSH minimal mode: drag in images/documents and invoke via folded context and Bash, keeping the minimal mode's original tool interface and system prompt unchanged.

#17·dsh-ocr-local

balcoz

6

Local image-to-text OCR plugin based on PP-OCRv5 and ONNX Runtime for offline recognition. Automatically invokes when pasting images in TUI or Web.

#18·dsh-windows-ocr

maxwell-feng

6

Enables text-only models to "see" images: uses Windows built-in OCR to recognize text from images locally, sending only the text to the model. Image data never leaves your machine.

#19·dsh-image-bridge

kbpoyo

5

Provides image bridging for DSH Web plain text model: saves pasted images to local paths and rewrites them as text markers for sending, allowing the model to independently call visual tools from its directory to view images.

#20·dsh-image-subagent

yuqingsh

5

Assists development of image-related features for the harness with subagent tooling.

#21·dsh-multimodal

MC5lan

5

Add vision and image generation to DeepSeek Harness: paste images for automatic transcription and continue conversation, generate images from descriptions, with fully user-configurable models and backends.

#22·dsh-vision-plugin

Agents365-ai

5

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

#23·dsh-vision-sidecar

121103qwq

5

Hosted free vision sidecar for DeepSeek Harness with durable session evidence

#24·dsh-imessage

photon-hq

4

Photon-hosted iMessage transport and settings UI for DeepSeek Harness

#25·dsh-imggenerate

Bald0Wang

4

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

#26·dsh-llm-vision-bridge

Einskyle

4

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)

#27·dsh-PaddleOCR-Skills

Aidenwu0209

4

PaddleOCR skills for DeepSeek Harness with native tools and GUI configuration

#28·dsh-tool-vision

Scorp1o117

4

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

#29·dsh-vision

Terry12138qy

4

Adds image recognition capabilities using cloud vision models with automatic failover.

#30·dsh-vision-bridge

GXX182

4

DeepSeek Harness plugin that bridges session images to pluggable vision APIs while keeping DeepSeek as the primary model.

#31·dsh-vision-provider

libinyam

4

Config-only DeepSeek Harness bundle for OpenAI-compatible vision models.

#32·ds-vision-plugin

Sorwcyra

4

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

#33·dsh-deepseek-vision

Argonaut790

3

Image understanding, OCR, and persistent visual evidence for text-only DeepSeek Harness models

#34·dsh-ernie-image

omdsh-dev

3

Provides image generation capabilities via the ERNIE model for creative tasks.

#35·dsh-image-inline

condaThinker

3

DSH plugin: show_image tool that renders an image inline into the web chat flow (QQ/WeChat style) — path text in the message, image bytes never enter model context.

#36·dsh-image-reader

zcXie777

3

Give DeepSeek Harness agents native image reading: a read_image tool backed by any OpenAI-compatible vision endpoint.

#37·dsh-image-tools

xiaoxianyu-office

3

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

#38·dsh-inline-images

3403473060

3

Render local image paths from assistant replies inline in the message body (9 formats, click-to-zoom lightbox, adjustable size).

#39·dsh-paddle-ocr

omdsh-dev

3

Integrates PaddleOCR for optical character recognition, extracting text from images.

#40·dsh-plugin-multimodal

shinjiyu

3

Vision sidecar for DeepSeek Harness: accept pasted images on text-only models.

#41·dsh-read-image

OoWJZZoO

3

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.

#42·dsh-vision

reimu-create

3

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

#43·dsh-vision-bridge

ximengxiaolan

3

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

#44·dsh-vision-plugin

woyeshishen

3

Likely adds vision capabilities to DeepSeek Harness, but details are unavailable.

#45·dsh-vision-primitives

zouyuanqing

3

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.

#46·file-drop/file-drop

xing666173

3

Enables drag-and-drop file uploads for the chat input area.

#47·free-vision-skill

niyongsheng

3

A local-only vision skill for macOS that enables image understanding without external APIs.

#48·dsh-deepseek-vision-router

mochgolf

2

Transparent image preprocessing route for DeepSeek Harness

#49·dsh-image-gen

LeemanCheung

2

GPT Image 2 generation with progressive Codex-style previews for DeepSeek Harness

#50·dsh-image-theme

Carpon39038

2

Warp-inspired image-to-theme plugin for DeepSeek Harness: upload a background, extract a palette, and apply a glass UI.

#51·dsh-image-to-path

cesaryike

2

Saves pasted or dragged images to the session workspace, passing file paths to text-only models.

#52·dsh-llm-deepseek-vision

NagasakiSoyo-ui

2

Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description

#53·dsh-mermaid-image-preview

baconbao

2

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

#54·dsh-mimo-vision-hint

Isekai-Mfu

2

DSH plugin: dispatch image-recognition tasks to an opencode-go mimo-v2.5 subagent via system-prompt injection

#55·dsh-ocr1-memory

DDDFXYqiming

2

Optical compression memory using DeepSeek-OCR (OCR1)

#56·dsh-plugin-image-wallpaper

CaoNing3212

2

Allows users to customize the visual theme of the DeepSeek Harness web interface with custom images.

#57·dsh-plugin-vision

tdf1995

2

Vision for text-only LLMs in DeepSeek Harness (DSH): describe images / OCR / VQA via free Gemini & GLM vision APIs

#58·dsh-read-image-view

Yu-tao-Li

2

Render read_image tool results as real images in the DSH Web GUI conversation flow (v0.1.0) · 在 DSH Web GUI 对话流中显示 read_image 读到的图片

#59·dsh-tesseract-ocr

maxwell-feng

2

Adds OCR capability to the agent by wrapping Tesseract, extracting text from images.

#60·dsh-tool-generate-image

zclDragon

2

dsh plugin: generate_image tool for text-only models via the Antigravity CLI (Gemini image generation).

#61·dsh-vision

xiaoshihou514

2

DeepSeek Harness: vision

#62·dsh-vision-bridge

lium970320

2

Bridges vision capabilities by converting images in sessions to text descriptions, enabling models without vision to process them.

#63·dsh-vision-helper

Yuuz12

2

DeepSeek Harness Vision Helper/DeepSeek Harness 视觉辅助方案

#64·dsh-vision-mix

haiziyao

2

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

#65·dsh-vision-skill

DDDFXYqiming

2

Vision skill plugin for DeepSeek Harness (image analysis and OCR)

#66·dsh-vision-tools

moon09300731

2

Adds vision understanding tools with paste, drag, and button inputs.

#67·dsh-w-vision/dsh-w-vision

wzxaaaa

2

Vision-related UI enhancements for the DSH ecosystem, with configurable display and hot-swap options.

#68·dsh-auto-vision

NormanFxxkingRockwell

1

Automatically detects configured multimodal models and adds vision capability to the main text-only model, returning recognition results as text.

#69·dsh-codex-image

xmasdong

1

Bridges DeepSeek with image generation and vision capabilities, routing requests to compatible backends.

#70·dsh-deepseek-vision

Cheng-cheng9669

1

DeepSeek web vision bridge plugin for DeepSeek Harness (DSH)

#71·dsh-eye-vision

AlloyPlane

1

Adds vision capabilities to DeepSeek Harness, likely enabling image processing or analysis.

#72·dsh-generate-image

zemul

1

Generates and edits images using the local OpenAI Codex CLI within DeepSeek Harness.

#73·dsh-image-describe

sd1g1

1

Adds a describe_image tool, allowing text-only models to understand image content.

#74·dsh-image-gen

hoyyang

1

Generates images via any OpenAI-compatible gateway or model with a visual config page and one-command invocation.

#75·dsh-image-gen

haimuhaimu

1

DeepSeek Harness plugin: generate images via Aliyun Bailian Qwen-Image (bl CLI). Adds a generate_image tool returning images as conversation attachments.

#76·dsh-imagegen-plugin

nexsjournal

1

Adds third-party image generation and editing capabilities to DSH, callable from chat and configured via a settings card, supporting multiple APIs.

#77·dsh-image-pathify

dami9527

1

Lets vision-less models process chat images by adding a built-in image recognition tool.

#78·dsh-image-plugins

alanzhao0128

1

Multimodal plugin for DeepSeek Harness (dsh): understand images and generate images via configurable OpenAI-compatible or DashScope endpoints.

#79·dsh-image-skin

Jack-sun-learner

1

Generates color themes from uploaded images and adds optional cute pet mascots.

#80·dsh-image-unlock

FrostLeafKEE

1

DeepSeek Harness 插件：解除 Web GUI 图片输入限制，图片附件文本化后交给 vision skill 识图 | dsh plugin that lifts the image-input gate and hands attachments to a vision skill

#81·dsh-image-vision

xsoc1

1

Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.

#82·dsh-image-vision-bridge

Icestab

1

Sends images from chat to a vision model for analysis, providing text descriptions to the main model.

#83·dsh-image-zoom

sijidoubi

1

DeepSeek Harness (dsh) client plugin: click-to-zoom lightbox for markdown/chat images

#84·dsh-img

gmleong

1

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。

#85·dsh-local-vision

hyls9527

1

DSH 插件：为纯文本模型提供本地看图能力（llama.cpp / Ollama / LM Studio / vLLM 全兼容）｜Local vision for text-only LLMs on any OpenAI-compatible local server

#86·dsh-luna-vision-bridge

ycp424c

1

DSH adapter that transcribes native image attachments with Codex Luna before delegating to DeepSeek

#87·dsh-mac-vision

Kevoyuan

1

On-device macOS OCR and Apple Vision for DeepSeek Harness — one native plugin with a bundled Skill.

#88·dsh-multimodal

chenkezhen480

1

Enables multimodal input and output capabilities for DeepSeek Harness, supporting images, audio, and video in conversations.

#89·DSH-Multimodal

yauntyour

1

Process multimodal files into text tokens for the model.

#90·dsh_omnivision

xiaozhengdeng

1

GUI agent plugin for DeepSeek Harness: OmniParser screen recognition, desktop automation, and an OmniVision vision dock

#91·dsh-plugin-image-tools

Pasumao

1

Adds image choice cards with zoom and inline images to enrich message presentation.

#92·dsh-plugin-mm-vision

Elohia

1

A plugin that adds multimodal vision capabilities to DeepSeek Harness.

#93·dsh-plugin-vision-toolkit

YYTbit

1

Vision toolkit for DeepSeek Harness -- give text-only agents eyes

#94·dsh-pseudo-vision

DDDFXYqiming

1

Local OCR, color-statistics, pixel-scan, and metadata bridge for text-only DeepSeek Harness models; no external vision API.

#95·dsh-screenshot-diff

PangYiMing

1

DSH plugin: pixel-diff two screenshots into diff.png + triptych (pixelmatch) — 像素对比工具

#96·dsh-tool-describe-image

sala003

1

Provides a tool for describing images, likely generating textual descriptions from visual input.

#97·dsh-tool-vision

gloryxpnv

1

Local-first vision for DeepSeek Harness: structured JSON evidence (OCR/layout/semantics) from local VLMs (LM Studio/Ollama), zero API cost, images never leave your machine.

#98·dsh-tool-vision

wanshichenguang

1

DSH plugin: image_describe (识图) tool over the DashScope OpenAI-compatible vision API (qwen3.7-flash). Bring your own DASHSCOPE_API_KEY.

#99·dsh-Unlimited-OCR-Skill

Aidenwu0209

1

Unlimited-OCR for DeepSeek Harness with a native tool and GUI configuration

#100·dsh-vision

sjakdhasdh

1

Vision tool plugin for DeepSeek Harness (DSH): give text-only models like deepseek-v4-flash image recognition via Alibaba Bailian / any OpenAI-compatible vision API. 给 DeepSeek Harness 无识图能力模型加识图工具。