Home Projects dsh-vision
dsh-vision
TypeScript

dsh-vision

Near-native image understanding for DeepSeek Harness

by oil-oil · GitHub
Stars
Forks
License
Created
Last commit
Language
deepseek-harnessdsh-pluginimage-understandingMITTypeScript
View on GitHub
In plain words

Enhance image understanding in DeepSeek by integrating vision capabilities with text models.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
dsh-vision — GitHub preview card
📈 Star history
📊 Star history will build up here over the coming days (1 data point recorded so far).
📈 Track dsh-vision

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Near-native image understanding for DeepSeek Harness

dsh-vision has 53 stars on GitHub. It has been forked 5 times. dsh-vision is written mainly in TypeScript. It has been in active development since 2026. dsh-vision is available under the MIT license. Its main topics are deepseek-harness, dsh-plugin, image-understanding, multimodal.

Frequently asked questions

What is dsh-vision?

Near-native image understanding for DeepSeek Harness

Is dsh-vision open source?

dsh-vision is an open-source project. It is released under the MIT license.

Is dsh-vision free?

Yes. dsh-vision is free and open source — you can use, modify and self-host it.

What license does dsh-vision use?

dsh-vision is available under the MIT license.

What language is dsh-vision written in?

dsh-vision is written mainly in TypeScript.

🏅 Maintainer of this project?
olud.ai badge — dsh-vision

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=oil-oil-dsh-vision)](https://olud.ai/project/oil-oil-dsh-vision.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
dsh-vision-router
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level v…
429 · deepseek-harness
sharesdeepseek-harnessvision
yao
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board,…
7.6k · agent
sharesdeepseek-harnessdsh-plugin
GLM-skills
Official skills for the GLM family of models.
459 · glm
sharesvisionmultimodal
agent-vision-toolkit
为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit…
946 · agent
sharesvisiondsh-plugin
claude-code-vision-skill
为 Claude Code 赋能多模态视觉能力,支持豆包、通义千问、GPT-4o 等模型,用于截图 / UI / 图表分析;适配 DeepSeek 等无视觉底座,搭配 browser-har…
162 · agent-skills
sharesvisionmultimodal
caffe
Caffe: a fast open framework for deep learning.
34.6k · deep-learning
sharesvision
Chat-UniVi
[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models…
941 · image-understanding
sharesimage-understanding
PixelRAG
The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.a…
9.6k · agent
sharesvisionmultimodal
Lance
A 3B-active-parameter native unified multimodal model for image and video understanding, genera…
1.3k · image-editing
sharesimage-understanding
coding-tools-mcp
Give any AI agent the ability to code
803 · dsh-plugin
sharesdsh-plugin

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.