dsh-vision-toolkit
让纯文本模型更好地做视觉任务的DeepSeek Harness插件：带意图的图片问答、长截图 OCR、UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
This plugin is a GitHub repository with the dsh-plugin topic — the repository README is the authoritative install source. Use the template below, adapting the package name / path from the README:
dsh plugin --profile web add $dsh-vision-toolkitLocal development? dsh --profile web --patch ./cordis.yml with an absolute plugin path — see Plugin Development.GitHub source? dsh plugin --profile web add github:$Anionex/$dsh-vision-toolkit — needs a prepare script in the repo (see packaging).
| Repository | Anionex/dsh-vision-toolkit |
| License | MIT |
| Category | Tool |
| Status | Community |
| Declared compatibility | not stated |
| Last commit | 2026-08-13 |
| Indexed | 2026-08-13 |
Declared is the author's claim; dsh.so has not independently tested it. See the changelog for version compatibility.
Built by DeepSeek, for DeepSeek — a Swift-native macOS coding agent
View
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics).
View为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
ViewQuestions or feedback? Official Discussions is the project’s canonical support channel; Discord has an active community. dsh.so itself improves via plugin submissions and your feedback.