meow-vision
Run the following command in DeepSeek Harness:
dsh plugin install meimiaoji-creator/meow-vision
Paste the following prompt into your AI chat to install this plugin:
You can install the meow-vision plugin in DeepSeek Harness by running the command `dsh plugin install meimiaoji-creator/meow-vision`, with the source code available at https://github.com/meimiaoji-creator/meow-vision。
About this plugin
In AI interactions, text models often cannot process images directly, while multimodal models, though capable of seeing images, lack real-time rendering preview capabilities for UI design iterations. The meow-vision plugin addresses these two pain points with its core tools: meow_vision enables text models to indirectly "see" images via a vision model and return text descriptions, compensating for the missing "eyes"; meow_preview renders Vue components, web pages, or local HTML files and takes screenshots, allowing multimodal models to intuitively view UI details like styles and layouts to accelerate component design iteration. This plugin is ideal for AI developers, UI engineers, and designers, especially those needing to leverage models for image processing or UI optimization, as it integrates seamlessly with DeepSeek Harness without source code modifications, offering a transparent and secure runtime experience.
Screenshots
Use Cases
- When text models process image screenshots or design drafts, call meow_vision for text descriptions.
- When multimodal models iterate UI components, use meow_preview to preview real rendering effects.
- In team collaboration, quickly view screenshots of local Vue demos or remote pages.
Best For
- AI developers needing to extend image processing capabilities of text models.
- UI engineers and designers for optimizing component styles and layout iteration.
- Product managers or testers for visualizing UI issues to accelerate feedback.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.