# dsh-llm-vision-bridge

> DeepSeek vision bridge for dsh: route image attachments to a vision model (Qwen3-VL via pi-ai/llama.cpp) and continue on a text-only LLM (DeepSeek)

## Metadata

- Author: [@Einskyle](https://github.com/Einskyle)
- Repo: <https://github.com/Einskyle/dsh-llm-vision-bridge>
- GitHub: [Einskyle/dsh-llm-vision-bridge](https://github.com/Einskyle/dsh-llm-vision-bridge)
- Stars: 4
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh`, `dsh-plugin`
- Forks: 0
- Open Issues: 1
- Last push: 2026-08-14T14:20:44.000Z
- Added: 2026-08-19T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add dsh-llm-vision-bridge
```

---

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