# dsh-plugin-multimodal

> Vision sidecar for DeepSeek Harness: accept pasted images on text-only models.

## Metadata

- Author: [@shinjiyu](https://github.com/shinjiyu)
- Repo: <https://github.com/shinjiyu/dsh-plugin-multimodal>
- GitHub: [shinjiyu/dsh-plugin-multimodal](https://github.com/shinjiyu/dsh-plugin-multimodal)
- Stars: 3
- Language: TypeScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh-plugin`, `vision`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-16T07:46:02.000Z
- Added: 2026-08-16T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add github:shinjiyu/dsh-plugin-multimodal
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-plugin-multimodal](https://deepseek-plugin.org/plugins/shinjiyu/dsh-plugin-multimodal)