dsh-vision
UnverifiedAdds vision to text-only DeepSeek via OpenAI-compatible VLM
Vision plugin for text-only DeepSeek Harness agents
This plugin adds vision capabilities to DeepSeek Harness agents, featuring a built-in free vision chain (no key required) and pixel-level vision tools such as Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, and screenshots. One-command install, no Python needed, and image turns work like ordinary tool-calling turns.

Official real work result screenshot provided by ysr666/dsh-vision-router.
View original media
Official real work result screenshot provided by ysr666/dsh-vision-router.
View original mediaBefore you install
This plugin has not completed plugin-level verification. Review the upstream README, required permissions, dependencies, and data flow first.
Taken from the author’s README. Follow the upstream instructions to install.
Loading upstream installation instructions…
Original documentation
Read the author’s README in place. Documentation and directory verification remain separate facts.
Loading the original README…
Adds vision to text-only DeepSeek via OpenAI-compatible VLM
Chrome sidebar extension for direct browser control
Vision bridge for image description