Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.
- GitHub stars
- 4
- License
- MIT
- Added
- 2026-08-14
GitHub info
- GitHub stars
- 4
- License
- MIT
- Primary language
- JavaScript
- Last push
- Aug 14, 2026, 2:20 PM
- Maintainer
- Einskyle
- Added
- 2026-08-14
Install
dsh plugin --profile web add dsh-llm-vision-bridgeREADME badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/Einskyle/dsh-llm-vision-bridge)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.