dsh-vision-toolkit
[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts.
DS
Anionex · Image & Photo Processing
STARS918
FORKS46
COMMITS0
CONTRIBUTORS0
VERSIONv0.1.48
UPDATED3 days ago
agent-skillsagent-vision-toolkitComputer VisiondeepseekMIT
Common commercial products in this category: Adobe Photoshop, Adobe Lightroom, Cloudinary
What can it do?
- Not just a caption — the content that matters. The model does not produce a generic description; it extracts evidence around the current task, such as “Where is the error?” or “Where is the button?”.
- A battle-tested visual-task methodology. The bundled Skill tells the agent what to look at for different visual tasks, which tool to choose, how to proceed, and how to verify the result.
Heads up
- • Website is unreachable (checked: 2026-10-31)