DSH Vision Toolkit DSH Vision Toolkit brings into DeepSeek Harness as a native Profile Bundle. Give text-only DSH agents eyes—and keep vision in the harness—with intent-aware image Q&A, OCR, original-pixel grounding, UI restoration, pixel verification, managed Artifacts, and Web Settings. Ten independent tools replace shell glue with structured schemas and Agent-scoped progressive exposure. Upstream toolkit: Anionex/agent-vision-toolkit · Project website: [agent-vision.anionex.me](h
| Stars | 861 |
| Forks | 45 |
| Language | TypeScript |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 73.736600822617/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-08 |
| Created | 2026-08-13 |
| Platforms | browser, node |
| Est. Tokens | ~22k |
These tools work well together with dsh-vision-toolkit for enhanced workflows:
Explore other popular ai 工具 tools:
dsh-vision-toolkit is [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. It is categorized as a AI 工具 with 861 GitHub stars.
dsh-vision-toolkit is primarily written in TypeScript. It covers topics such as agent-skills, agent-vision-toolkit, computer-vision.
You can find installation instructions and usage details in the dsh-vision-toolkit GitHub repository at github.com/Anionex/dsh-vision-toolkit. The project has 861 stars and 45 forks, indicating an active community.
dsh-vision-toolkit is released under the MIT license, making it free to use and modify according to the license terms.