dsh-vision
UnverifiedAdds vision to text-only DeepSeek via OpenAI-compatible VLM
Vision bridge for image description
Adds a describe_image tool to DeepSeek Harness, converting images into text descriptions via the mimo-v2.5 model, integrated through the ctx.fs and ctx.credentials seams.
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
Dual-agent visual novel stage