What it may solve
Visual model adapter for Codex and DeepSeek Harness, powered by PaddleOCR-VL and Qwen.
Imported third-party catalog description; not a Registry verification conclusion.duhai-vision
Source candidateVisual model adapter for Codex and DeepSeek Harness, powered by PaddleOCR-VL and Qwen.
Author: hamliy-feng · Vision & Multimodal · Catalog snapshot: 2026-09-05Sources and public signals
0 stars · — downloads
Signals were provided by the source catalog and do not imply quality or safety. 2026-09-05What can currently be confirmed
DSH compatibility
No exact-version test is available.
Security analysis
No Registry security conclusion is available.
Functional verification
No functional smoke evidence is available.
Permissions
Plugin permissions have not been resolved.
Exact artifact
Version and integrity have not been resolved.
Continue checking with the plugin manager
Describe your task in a DSH conversation and mention duhai-vision. The plugin manager can find this candidate through Registry, then inspect its actual source and version locally.
Sources available for local inspection
- GitHub source
github:hamliy-feng/duhai-visionExact version not resolved