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.
About
One-line take: most dsh vision plugins turn images into text descriptions for DeepSeek (description bridge — lossy); this plugin hands the image turn straight to a vision model (routing bridge — pixel-level), with a built-in keyless free fallback.
Open Source Health
- Stars
- 1,101
- Forks
- 47
- License
- MIT
- Last commit
- 26 days ago
Resources & Links
Related Categories
Vendor
Shirui
Xi'an Jiaotong University, Engineering Experimental Class
Quick Links
Open Source
Related Products
OCRmyPDF
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
Top category match
ZenlessZoneZero-Auto
绝区零 | ZenlessZoneZero | 零号空洞 | 自动战斗 | 自动化 | 图片分类 | OCR识别
Top category match
PaddleOCR2Pytorch
PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
Top category match
MinerU
A practical document parsing tool for converting PDF, images, DOCX, PPTX, and XLSX into Markdown and JSON
Top category match
Deepseek OCR App
A quick vibe coded app for deepseek OCR
Top category match