dsh-client-vision
Likelyby ankye · Vision & Media
Give your DeepSeek Harness agent eyes. dsh-client-vision is a screen-capture + external image-recognition plugin for DeepSeek Harness: the agent takes a screenshot (or points at any image), hands it to a vision-capable model through a pluggable channel, and gets back plain text it can actually act on — no multimodal model required.
Likely plugin
Follows the dsh package or skill conventions, but we found no direct runtime dependency.
What we found in the repo
- — npm package dsh-client-vision
Installing
No published npm package was found. Clone the repository and follow its README to build from source.
Before you install
A listing here is not a security audit. The tier above records whether this repo is wired as a real dsh plugin — not whether it is safe to run. A plugin executes with your agent's permissions: your files, your shell, your network. How to vet a dsh plugin before installing
Found malware or an impersonation in this repo? Report this listing
Repository details
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Language
- TypeScript
- License
- MIT
- Created
- 2026-08-19
- Last push
- 2026-08-19
Topics
More in Vision & Media
dsh-vision-router
Verifiedysr666
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.
dsh-vision
Verifiedoil-oil
Near-native image understanding for DeepSeek Harness
dsh-plugin-mineru
VerifiedHuanLinOTO
向模型暴露 MinerU 文档解析工具，将 PDF/图片/DOCX/PPTX/XLSX 转为结构化 Markdown/JSON | Exposes MinerU document-parsing tools to the model, converting PDF/images/DOCX/PPTX/XLSX into structured Markdown/JSON
dsh-vision
Verifiedwilliam-jin-cmu
dsh 插件：给纯文本 DeepSeek 加视觉——view_image 工具桥接任意 OpenAI 兼容 VLM（默认智谱免费档，实测 4 厂商 10 模型）
picturereader
Verifiedjing-hy
DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.
dsh-openmaic
VerifiedTHU-MAIC
OpenMAIC for DeepSeek Harness: classrooms, slides, interactive widgets, and Socratic teaching