DeepSeek Harness native plugin: vision capabilities for text-only LLMs (describe, OCR, VQA, layout analysis, clipboard)
Description collected from the plugin's own repository or package metadata.
npx @deepseek-ai/dsh plugin add dsh-plugin-deepeye
@Flyvhidbwo
DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text via any OpenAI-compatible VLM before delegating to the text-only DeepSeek adapter. GUI image attachments work
@linenxi-ctrl
Add external image recognition models to DeepSeek Harness: circular whale button, send image for recognition with automatic return, model autonomous screenshot + image recognition tool, multi-protocol auto-adaptation, one-click installation for beginners (automatically downloads Node.js if not installed)
@oil-oil
Near-native image understanding for DeepSeek Harness