# dsh-autovision

> dsh-autovision: paste an image into a text-only model composer and a configured multimodal model transcribes it to text automatically. Twin-provider auto-routing + agent-callable read-image tool. No built-in keys, no relay.

## Metadata

- Author: [@Junkrat9527](https://github.com/Junkrat9527)
- Repo: <https://github.com/Junkrat9527/dsh-autovision>
- GitHub: [Junkrat9527/dsh-autovision](https://github.com/Junkrat9527/dsh-autovision)
- Stars: 0
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh-plugin`, `vision`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-18T10:37:02.000Z
- Added: 2026-08-18T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add @iroam2375/dsh-autovision
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-autovision](https://deepseek-plugin.org/plugins/Junkrat9527/dsh-autovision)