# sidesight

> CLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.

## Metadata

- Author: [@ZhuXinAI](https://github.com/ZhuXinAI)
- Repo: <https://github.com/ZhuXinAI/sidesight>
- GitHub: [ZhuXinAI/sidesight](https://github.com/ZhuXinAI/sidesight)
- Stars: 1
- Language: TypeScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `agent-skills`, `agentic-workflow`, `claude-code`, `claude-skills`, `codex`, `cordis`, `deepseek`, `dsh-plugin`, `glm`, `harness`, `harness-engineering`, `hermes-agent`, `image-to-text`, `multimodal`, `ocr`, `openclaw`, `pi-agent`, `text-only-llm`, `vision`, `vision-transformer`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-14T05:37:07.000Z
- Added: 2026-08-14T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add github:ZhuXinAI/sidesight
```

---

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