DeepSeek Harness插件市场
返回目录
文件与数据插件新

dsh-vision-router

ysr666/dsh-vision-router

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.

去 GitHub 查看项目主页

OVERVIEW

数据概览

Star
71
Fork
8
开放 Issue
3
最后推送
2026/08/15 10:55:20

PROJECT TOPICS

项目标签

deepseek-harnessdshdsh-pluginmultimodalvision
PROJECT README README展开收起

正在读取 GitHub README...

MORE IN CATEGORY

同类插件

浏览分类
文件与数据技能精选

modlens

liustack

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网第一个 DeepSeek Harness 视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

agent-skillsclaude-code
1.4kTypeScript2026-02-22
文件与数据新技能精选

dsh-vision-toolkit

Anionex

让纯文本模型更好地做视觉任务的DeepSeek Harness插件：带意图的图片问答、长截图 OCR、UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

agent-skillsagent-vision-toolkit
348TypeScript2026-08-13