dsh-see-now
SAOS-3624
让 AI 实时看见你的屏幕:按变化量筛选帧、多帧拼进一张图,静止画面几乎不花 token
ysr6661,26161Updated today
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image and it just works — no Python, one-command install.
Practical score
83 / 100
Setup
Needs setup
License
MIT
Language
JavaScript
Copy the command, or hand the whole task to your harness agent.
git clone https://github.com/ysr666/dsh-vision-router.gitPlease install the DeepSeek Harness plugin "ysr666/dsh-vision-router" for me. - GitHub repository: ysr666/dsh-vision-router (https://github.com/ysr666/dsh-vision-router) - Type: a Cordis plugin (installed into a DSH profile) - The plugin declares a DSH version…
A cleaned excerpt from the project's own documentation.
dsh-vision-router Turn vision on when you need it — eyes for text-only agents on DeepSeek Harness. Free out of the box, no key, no Python, one command. DeepSeek keeps thinking; the built-in free vision chain and fourteen deep tools do the seeing. When an image matters, enable the composer’s “👁 Vision” control and use image turns like ordinary tool-calling turns — grounded, measurable, repeatable.
Open on GitHubSimilar tools from the same corner of the ecosystem.
SAOS-3624
让 AI 实时看见你的屏幕:按变化量筛选帧、多帧拼进一张图,静止画面几乎不花 token
momasiku
DeepSeek Harness 的桌面自动化:给整台 Windows 机器装上眼睛和手。可以做人能做的任何事,包括且不仅限于CAD,WPS,浏览器操作,发微信。安全,快速,可靠,聪明,人性化。
anweat
Self-contained browser runtime plugin: Playwright (chromium) + OpenCLI as plugin-local deps (global reuse fallback), exposes a `browser` service and interactive browser tools.