DSHUNIVERSE
Back to catalog

GITHUB TOPIC

image

21projects include this topic

The "image" topic on GitHub groups 21 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by tongflow with 937 GitHub stars. tongflow — TongFlow — Multimodal GenAI Studio. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.

{count} projects

Exact GitHub Topic match

Files & dataPlugin

tongflow

tong-io

TongFlow — Multimodal GenAI Studio

Structure check pending
3dagentaiai-tools
937 125 7
1 months
Files & dataPlugin

[Discontinued] DeepSeek Harness vision bridge plugin: the new Harness natively supports image recognition, please use the native capability, this repository is for historical reference only.

Structure check pending
agentaiattachmentchat
4 0 0
1 months
Files & dataPlugin

DeepSeek Harness plugin: lets models that can't see images, such as deepseek-v4-flash, handle chat images too, with a built-in image recognition tool. Install: dsh plugin --profile web add dsh-image-pathify

Structure check pending
deepseekdeepseek-harnessdshdsh-plugin
4 0 0
7 days
Files & dataPlugin

Silent vision bridge for DeepSeek Harness: route chat images to a fixed vision model, preserve UI originals, and reuse observations across compaction and restarts.

Structure check pending
deepseek-harnessdshdsh-pluginimage
2 0 0
1 months
Files & dataSkill

dsh-vision-skill

DDDFXYqiming

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

Structure check pending
agent-skillsdeepseek-harnessdshdsh-plugin
2 0 0
1 months
Files & dataPlugin

A DeepSeek Harness tool plugin that lets text-only agents "see" local images — auto-detects the real format and returns a detailed text description via any OpenAI-compatible vision model.

Structure check pending
cordis-plugindeepseek-harnessdsh-pluginimage
2 0 0
1 months
Files & dataPlugin

Give DeepSeek Harness text-only models vision: Codex-style drag-and-drop of images into the chat box automatically routes them to the user-configured vision model for text conversion, v4 reads images without switching models. 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.

Structure check pending
codex-styledeepseek-harnessdsh-pluginimage
2 0 0
1 months
Files & dataPlugin

mimo-vision

wulusai2333

DeepSeek Harness (DSH) native plugin — describe_image tool: a vision bridge (image → mimo-v2.5 → text description) over the ctx.fs / ctx.credentials seams

Structure check pending
agentcordisdeepseek-harnessdsh
2 0 0
1 months
Files & dataPlugin

DSH chat input box image tool (self-developed): upload images + region screenshot, injects into the draft image track. Zero dependencies, pure client-side + Electron desktopCapturer screenshot.

Structure check pending
composerdeepseek-harnessdesktopcapturerdsh
1 0 0
1 months
InterfacePlugin

The best image viewing plugin in the DSH ecosystem: eight formats PNG/JPEG/GIF/WebP/BMP/SVG/ICO/AVIF, SVG rendered safely only; requires dock and dock-files | The best image viewer for DSH: PNG/JPEG/GIF/WebP/BMP/SVG/ICO/AVIF with SVG rendered safely only; requires dock and dock-files

Structure check pending
cordisdeepseek-harnessdshdsh-plugin
1 0 0
1 months
Files & dataPlugin

dsh-Sight

cransmathenia666-hash

Give text-only DeepSeek Harness (dsh) agents vision — pasted images auto-convert to text descriptions with persistent caching, each image converted only once.

Structure check pending
deepseek-harnessdshdsh-pluginimage
1 0 0
1 months
Files & dataSkill

dsh-picture-fit

cyanfish-x

DSH plugin + Agent Skill: auto-fit oversized images with sharp before attachment admission

Structure check pending
agent-skilldeepseekdeepseek-harnessdsh
1 0 0
1 months
Files & dataPlugin

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

Structure check pending
deepseek-harnessdsh-pluginimagelightbox
1 0 0
1 months
Files & dataPlugin

dsh-vision-bridge

Xieweikang123

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

Structure check pending
deepseek-harnessdsh-pluginimageocr
1 0 0
1 months
Files & dataPlugin

dsh-vision

zoahdev

Give DeepSeek Harness eyes: analyze images with an OpenAI-compatible vision model via a vision_analyze tool.

Structure check pending
agentdeepseek-harnessdsh-pluginimage
1 0 0
1 months
Files & dataPlugin

DSH plugin: auto-downscale oversized image attachments (2000px / 3.5MB / 40 megapixels)

Structure check pending
deepseek-harnessdshdsh-pluginimage
1 0 0
1 months
Files & dataPlugin

Persistent vision sub-agent plugin: auto conversion of pasted images, describe_image tool, per-session isolated conversation memory with status capsule + detail page (DeepSeek Harness)

Structure check pending
deepseek-harnessdsh-pluginimagevision
0 0 0
1 months
InterfacePlugin

Annotate a pending composer image in place (pen / box / arrow / typed text) and insert the PNG back next to the original. Minimal footprint: nothing in DSH UI is restyled, no host routes, no dependencies.

Structure check pending
annotationcomposerdeepseekdeepseek-harness
0 0 NaNm
17 days
Files & dataPlugin

No project description provided yet.

Structure check pending
composerdeepseek-harnessdsh-pluginimage
0 0 0
1 months
Files & dataPlugin

DSH plugin: keep text-only DeepSeek models (V4-Flash / V4-Pro) and auto-route image-bearing requests to the official vision model (deepseek-v4-flash-vision-exp) - no manual model switching.

Structure check pending
deepseekdeepseek-harnessdshdsh-plugin
0 0 0
1 months
DSH PluginsPlugin

DSH (cordis) plugin: browse, preview, download and delete generated images and videos from a semi-transparent sidebar popup.

Structure check pending
cordisdeepseek-harnessdshdsh-plugin
0 0 NaNm
15 days