cjz-wr/background-plugin
cjz-wr★ 1TypeScript最后同步: 2026-08-16
修改DSH的背景,支持静态动态背景,支持网页图片视频,支持修改透明度
README 摘要
dsh-background English 中文 DeepSeek Harness plugin: Background plugin. Supports local or online images/videos, and allows adjusting the opacity. Settings UI Install From the Web 插件 (Plugins) settings surface, search this repository and click install, or from the CLI: Replace with your own profile, usually web , for example: A newly installed bundle layer composes on the next process boot. Build output is committed on purpose. Git installs pull the repository as it is — nothing runs your build script. lib/ is therefore committed so git/npm/tarball installs all work with zero build authorization; there is no prepare script. Rebuild locally with npm run build and commit the new lib/ whenever src/ changes. ⚠️ Conflict only with builds that already compose this row. The official DeepSeek Harness does NOT ship it — this bundle is a standalone add-on and installs cleanly into any profile. The one exception: this package was extracted from a repo whose packages/bundle/web-app/cordis.patch.yml already composes a row with the id ui-background . Mounting this bundle on top of such a build fails at boot with duplicate loader entry id: ui-background ; install it into a profile that does not incl…
在 GitHub 查看完整 README →分类
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). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
★ 2,346
Anionex/agent-vision-toolkit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
★ 946
Anionex/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.
★ 517