dsh-vision
UnverifiedAdds vision to text-only DeepSeek via OpenAI-compatible VLM
Screen capture and external vision for DSH
A screen-capture and external image-recognition plugin for DeepSeek Harness, enabling agents to take screenshots or point at images, send them to a vision-capable model via a pluggable channel, and receive actionable text without needing a multimodal model.
Before 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
