DSH Plugins

dsh-vision-toolkit

by Anionex · Anionex/dsh-vision-toolkit

Manifest valid

880 Stars

46 Forks

4.3k Downloads/week

9 Open issues

Updated: Sep 12, 2026

Install

dsh plugin --profile web add @anionex/dsh-vision-toolkit
GitHubnpmHomepage

MIT

TypeScript

Original language: English

UI (client)hasBundlePatch

About

Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.

Compatibility

DSH 0.1.5-rc.2: worksDSH 0.1.5-rc.1: worksDSH 0.1.5-alpha.2: errorDSH 0.1.2-rc.1: errorDSH 0.1.5-alpha.1: errorDSH 0.1.1-rc.2: worksDSH 0.1.0-rc.8: worksDSH 0.1.3-alpha.2: errorDSH 0.1.2-alpha.5: errorDSH 0.1.2-alpha.4: errorDSH 0.1.2-alpha.3: errorDSH 0.1.2-alpha.2: error

Versions

Latest versionPublishedSize
0.1.13
0.1.14
0.1.15
0.1.16
0.1.17
0.1.18
0.1.19
0.1.20
0.1.21
0.1.22
0.1.23
0.1.24
0.1.25
0.1.26
0.1.27
0.1.28
0.1.29
0.1.30
0.1.31
0.1.32

Similar plugins

dsh-vision-router

by ysr666

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

Vision & MultimodalModels & ProvidersManifest valid

1.1k

8.7k/wk

MIT

JavaScript

Sep 13, 2026

dsh plugin --profile web add dsh-vision-router

by sfyyy

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

Manifest valid

6

MIT

JavaScript

Aug 16, 2026

dsh plugin --profile web add @dsh-extension/dsh-vision-bridge

Model-facing image_describe (识图) tool over the DashScope OpenAI-compatible API (qwen3.7-flash), plus a paste bridge: on text-only sessions, pasted images auto-convert to file paths at send time and re

Vision & MultimodalManifest valid

0

dsh plugin --profile web add dsh-tool-vision

by GZX2211

专为 DeepSeek Harness Web GUI 打造的可视化多 Agent 工作流编排插件。公开测试版已上线!接下来会随着 DSH 的正式版上线一并发布正式版! 1. 更新:该插件目前已对齐最新候选版 dsh v0.1.5-rc.1,不适配 Alpha 版。2. 声明:由于该插件编排层依赖官方父子代理交互规则,对于强破坏性变更的版本,不准备适配,因为真的很难修!

Manifest valid

26

MIT

TypeScript

Sep 13, 2026

dsh plugin --profile web add dsh-visual-workflow

by FuzzySoul

为DSH(DeepSeek Harness)量身打造的视觉插件,现已支持agent调用图片显示/Vision plugin for DSH(DeepSeek Harness),support Proactive Image Display.

Vision & MultimodalManifest valid

7

MIT

JavaScript

Aug 19, 2026

dsh plugin --profile web add dsh-free-vision

by CaseyTso

给纯文本 DeepSeek Harness 模型加上识图能力:analyze_image 把图片转发到任意 OpenAI 兼容视觉端点 | Vision bridge for text-only DSH models

Manifest valid

0

MIT

JavaScript

Aug 18, 2026

dsh plugin --profile web add analyze-image-tool