DSH Image Vision
☆ 0Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.
Get this plugin
Review the source, then continue to the publisher.
dsh plugin --profile web add dsh-image-visionRepository signals
Source snapshot 8/18/2026No repository documentation has been imported yet. The signals below come from this repository's public GitHub metadata.
- Created
- Aug 15, 2026
- Last push
- Aug 15, 2026 · 1 months ago
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Language
- TypeScript
- License
- Non-standard
- Registry
- npm
More from xsoc1
View publisher →Related DeepSeek Harness Plugins
Browse UI & Design →
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
DeepSeek Harness 可编辑设计系统：AI 生成、可视化编辑、模板市场与 PPT｜Native Design & PPT Studio for DeepSeek Harness.