dsh-plugin-deepeye
Run the following command in DeepSeek Harness:
dsh plugin install Favio8/dsh-plugin-deepeye
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command dsh plugin install Favio8/dsh-plugin-deepeye. The full source code is available at https://github.com/Favio8/dsh-plugin-deepeye.
About this plugin
Pure text models in DeepSeek Harness, such as DeepSeek, cannot process images, hindering users from analyzing pictures or performing visual tasks. The dsh-plugin-deepeye plugin solves this by offering native vision capabilities through Cordis integration, effectively giving models "eyes" to see and interpret images. Core features include detailed image description, OCR text extraction, visual question answering, UI layout analysis, clipboard screenshot analysis, and automatic translation of pasted images—allowing users to paste images directly into text model sessions where the model understands the content textually. This plugin is ideal for developers, researchers, or anyone needing to enhance visual processing in DeepSeek Harness, whether for image analysis, automation tasks, or seamlessly integrating image information into text-based conversations.
Use Cases
- Analyze image content and generate descriptions
- Automatically extract text information from screenshots
- Paste images in text-based conversations for understanding
Best For
- AI developers needing to add vision capabilities to models
- Researchers performing image data analysis tasks
- Users wanting to handle image information seamlessly in chats
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.