dsh-llm-deepseek-vision

Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description

Star

2+1

7-day growth

Contributors

Language

TypeScript

Updated

2026-08-14

Requires a manual build

This is a bundle, but the author hasn't published to npm, the package entry points at build output (lib/ or dist/), and the repo has no prepare script. Installing straight from git only pulls uncompiled source and the entry won't be there at load time. Build it locally first, then install it by path:

git clone https://github.com/NagasakiSoyo-ui/dsh-llm-deepseek-vision.git
cd dsh-llm-deepseek-vision
pnpm install && pnpm build
dsh plugin --profile web add .

The name after --profile is a profile name you choose yourself — swap in whichever one you use.

Share card

Drop it into your README — it links back to this page.

Badge (inline)

[![dshfind](https://dshfind.com/api/badge/NagasakiSoyo-ui/dsh-llm-deepseek-vision)](https://dshfind.com/en/plugins/NagasakiSoyo-ui/dsh-llm-deepseek-vision?ref=badge)

Card (440×200)

[![dshfind](https://dshfind.com/api/card/NagasakiSoyo-ui/dsh-llm-deepseek-vision)](https://dshfind.com/en/plugins/NagasakiSoyo-ui/dsh-llm-deepseek-vision?ref=badge)

#llm #plugin #vision