Gives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.
- GitHub stars
- 10
- License
- MIT
- Added
- 2026-08-15
GitHub info
- GitHub stars
- 10
- License
- MIT
- Primary language
- TypeScript
- Last push
- Aug 21, 2026, 3:57 AM
- Maintainer
- jyh20030112
- Added
- 2026-08-15
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
Animated demo of the vision bridge in dsh web: the user sends an image, the vision bridge auto-describes it, and the main model answers from the description
https://raw.githubusercontent.com/jyh20030112/dsh-visual-plugin/main/assets/vision-bridge-flow.svg
Vision Bridge configuration card in the settings plugin configuration tab
https://raw.githubusercontent.com/jyh20030112/dsh-visual-plugin/main/assets/vision-bridge-config.png
Install
dsh plugin --profile web add github:jyh20030112/dsh-visual-pluginTags
README badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/jyh20030112/dsh-visual-plugin)Related plugins
Vision & Multimodalmodlens
★ 3768Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-vision-router
★ 1030Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
dsh-vision-toolkit
★ 842Vision 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.