Development and design teams using text-only agents that need to read screenshots and images.
git clone https://github.com/Anionex/dsh-vision-toolkit.gitThird party software. By copying, downloading or installing it you accept the Academy legal notice: you are responsible for reviewing its code and permissions before use.
Loading the file...
A vision toolkit that lets text-only DeepSeek Harness agents work with images. It covers image questions and answers, OCR on long screenshots, restoring a UI from a screenshot, grounding, pixel diff, artifacts and a web interface.
Development and design teams using text-only agents that need to read screenshots and images. A vision toolkit that lets text-only DeepSeek Harness agents work with images. It covers image questions and answers, OCR on long screenshots, restoring a UI from a screenshot, grounding, pixel diff, artifacts and a web interface.
Run this in your terminal: git clone https://github.com/Anionex/dsh-vision-toolkit.git
Yes. The code is on GitHub (Anionex/dsh-vision-toolkit) under the MIT licence.
It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.