Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evidence memory, and a polished client panel.
메모리 및 지식 · 시각 도구
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:54xkeee/dsh-youreyes
OpenAI-compatible image generation for DeepSeek Harness: text-to-image, image editing and batch generation, with the pictures rendered straight in the conversation — 通过 OpenAI 兼容接口生图与修图。
시각 도구 · 인터페이스 확장
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Cikian/dsh-cture-image
Plug-and-play image reading for text-only models: admits pasted images, projects them as [Image #N], and provides a first-class read_image tool backed by a configurable vision model, with a 读图 settings page (设置 → 读图) bridged over typert Remote.
Agent 협업 · 시각 도구 · 서비스 연동 · 생산성 도구
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:OoWJZZoO/dsh-read-image
Tianlight skin for the dsh web GUI: Makoto Shinkai daylight skies, a looping video wallpaper, a wallpaper library with upload/rotation, optional WebWallGL scene support, and a draggable Mint chibi-cat desktop companion
스킬 · 시각 도구 · 인터페이스 확장
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MilkySnowWay123/dsh-client-ui-skin-tianlight
A DeepSeek Harness (DSH) plugin that reads PDF files of any size (no 64KB limit): full Unicode text extraction (Chinese/English) via pdfjs-dist, with automatic OCR for scanned or image-heavy pages (Windows WinRT OCR zh-Hans-CN + en-US, or optional tesseract.js).
시각 도구
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:henryxiao709/dsh-pdf
Paste images / drag any files into the DSH composer -> saved into the session workspace as files -> images read by modlens, other files read by the model by path
시각 도구 · 생산성 도구
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LQ-1123/paste-to-workspace