X

ximengxiaolan/dsh-vision-bridge

“Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only…”

OverviewREADME

TL;DR

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

30 days of GitHub stars

-1 stars

-33.3% observed change

Sep 1+0 stars3 totalSep 2+0 stars3 totalSep 3+0 stars3 totalSep 4+0 stars3 totalSep 5+0 stars3 totalSep 6+0 stars3 totalSep 7+0 stars3 totalSep 8+0 stars3 totalSep 9+0 stars3 totalSep 10+0 stars3 totalSep 11+0 stars3 totalSep 12+0 stars3 totalSep 13+0 stars3 totalSep 14+0 stars3 totalSep 15+0 stars3 totalSep 16+0 stars3 totalSep 17+0 stars3 totalSep 18+0 stars3 totalSep 19-1 stars2 totalSep 20+0 stars2 totalSep 21+0 stars2 totalSep 22+0 stars2 totalSep 23+0 stars2 totalSep 24+0 stars2 totalSep 25+0 stars2 totalSep 26+0 stars (estimated)2 totalSep 27+0 stars (estimated)2 totalSep 28+0 stars2 totalSep 29+0 stars2 totalSep 30+0 stars2 total

Sep 1Sep 15Sep 30

Also in this category

4 items

T

Other

tt-a1i/archify

Generate validated, self-contained interactive architecture, workflow, sequence, data-flow, and lifecycle diagrams from repositories or system descriptions.

★ 74.2K

T

Other

Tencent/BrowserSkill

BrowserSkill bridge for controlling visible Chrome and Edge Agent Windows from DeepSeek Harness, with native browser tools, accessibility and VOM observations, screenshots, owned multi-session control, and a live Web UI overlay.

★ 7.9K

L

Other

liustack/modlens

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

★ 4.1K

Y

Other

YuJunZhiXue/dsh-purge

Adds a Settings card to edit prompt-inject.md, manage AGENTS.md or CLAUDE.md rule sets, check for plugin updates, and apply or restore reversible local package updates.

★ 2.7K