GitHub · 多媒体与视觉
314857493/dsh-visionvision-tool
Model-facing vision tool for DeepSeek Harness: describe and OCR image files by calling the free Zhipu GLM vision API directly (glm-4v-flash fallback chain), no external CLI required.
SOURCE-DECLARED INSTALL
Open the public source page ↗MEDIA REFERENCES
Captured in public view
REGISTRY LISTINGS
Source-attributed install evidence
| Registry source | Install spec | Version | Verification claim | Observed | Raw snapshot |
|---|---|---|---|---|---|
| awesome-dsh-plugin/awesome-dsh-plugin · README.md | — | — | unreported | 2026-08-17 → 2026-08-17 | 1121 |
Verification is a claim made by the named Registry Source; it is not a security, compatibility, quality, or official-endorsement claim by this site.
CONTEXT
Why it is here
Model-facing vision tool for DeepSeek Harness: describe and OCR image files by calling the free Zhipu GLM vision API directly (glm-4v-flash fallback chain), no external CLI required.
Evidence updated 2026-08-17T13:07:24Z. Interaction numbers are platform-native snapshots; the evidence panel records the metric source and observation time. NULL means the public page did not expose a number at collection time.