# dsh-vision-bridge

> Vision bridge for DeepSeek Harness: images are described by the vision model you pick, so a text-only chat model never fails a turn on a picture

## Metadata

- Author: [@GooDAnDReaDY](https://github.com/GooDAnDReaDY)
- Repo: <https://github.com/GooDAnDReaDY/dsh-vision-bridge>
- GitHub: [GooDAnDReaDY/dsh-vision-bridge](https://github.com/GooDAnDReaDY/dsh-vision-bridge)
- Stars: 0
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh`, `dsh-plugin`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-19T18:41:07.000Z
- Added: 2026-08-19T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add @goodandready/dsh-vision-bridge
```

---

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