DSHUNIVERSE
Back to catalog

GITHUB TOPIC

image-understanding

12projects include this topic

The "image-understanding" topic on GitHub groups 12 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-vision with 88 GitHub stars. dsh-vision — Near-native image understanding for DeepSeek Harness. 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

dsh-vision

oil-oil

Near-native image understanding for DeepSeek Harness

Structure check pending
deepseek-harnessdsh-pluginimage-understandingmultimodal
88 8 2
1 months
Models & MCPPlugin

dsh-AuthInOne

Stormycry-cryp

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

Structure check pending
cost-attributioncost-trackingcustom-apideepseek-harness
75 0 0
1 months
Files & dataPlugin

DeepSeek Harness plugin: DeepSeek Pro brain + automatic image recognition. Images attached in the GUI are processed by default with the official deepseek-v4-flash-vision-exp native vision model, converted to text, and passed to DeepSeek for answers (even text-only V4-Pro can see images); supports any OpenAI-compatible VLM such as Bailian/Zhipu/OpenRouter; auto-detects local Ollama without a key; one-question confirmation during install

Structure check pending
dashscopedeepseek-harnessdsh-pluginimage-understanding
15 0 0
1 months
Files & dataPlugin

A vision plugin built for DSH (DeepSeek Harness), now supports Agent-invoked image display / Vision plugin for DSH(DeepSeek Harness),support Proactive Image Display.

Structure check pending
deepseek-harnessdshdsh-pluginfree
7 1 0
1 months
Files & dataPlugin

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

Structure check pending
agentdeepseekdeepseek-harnessdsh
6 0 0
1 months
Files & dataPlugin

DeepSeek Harness plugin: describe_image — give a text-only model vision through an OpenAI-compatible VLM endpoint

Structure check pending
deepseekdeepseek-harnessdescribe-imagedsh
6 1 1
1 months
Files & dataPlugin

dsh-eye-vision

AlloyPlane

This repository does not provide a project description yet.

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

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

Structure check pending
ai-agentscomputer-visiondeepseekdeepseek-harness
2 0 1
1 months
Files & dataPlugin

dsh-llm-vision

1710782766

Reliable vision + OCR for text-only models on DeepSeek Harness: describe_image (normal/critical) + extract_text tools, auto-preprocessing, retries, and a persistent answer cache.

Structure check pending
deepseek-harnessdshdsh-pluginimage-understanding
1 0 0
1 months
Models & MCPSkill

prismrelay-mcp

Arnoldkevin

Vision-first local MCP that gives text-only Agents image understanding through Agnes AI (BYOK).

Structure check pending
agent-skillscomputer-visiondeepseekdeepseek-harness
1 0 0
1 months
Files & dataPlugin

dsh-vision-link

sprainJinyu

Route-preserving image understanding for text-only models in DeepSeek Harness (DSH).

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

dsh-visionary

zhuiyueya

Give text-only DeepSeek models eyes — a DeepSeek Harness plugin that transparently converts chat images into OCR text + vision-model descriptions before they reach the LLM. Configure vision backends (GLM-4V, Qwen-VL, Gemini, Ollama…) right in the Models settings page; multi-backend fallback chain, double-layer caching, no config files.

Structure check pending
deepseekdeepseek-harnessdsh-pluginimage-understanding
0 0 0
1 months