zjcdkj/dsh-plugins
zjcdkj★ 0JavaScriptLast synced: 2026-08-16
DeepSeek Harness (DSH) plugins. qwen-image gives a text-only coding model eyes: an image goes to a Qwen-VL route through ctx.llm and comes back as text, so DeepSeek keeps coding while Qwen looks. Pure ESM, no build permission at install. | DSH 插件集:qwen-image 让纯文本模型借千问 VL 读图,返回文本;纯 ESM,安装无需构建授权。
README excerpt
dsh-plugins English 中文 Plugins for DeepSeek Harness. Each package under packages/ is published to npm on its own and installs independently — nothing here requires the others. Plugins Plugin npm What it does qwen-image dsh-plugin-qwen-image Gives a text-only coding model eyes. A local image goes to a vision route through ctx.llm and comes back as text, so DeepSeek keeps driving the session while Qwen does the looking. It finds a vision route on its own, so a dsh that already reaches one needs no configuration. Install Pick the package you want; the repository layout does not matter to the installer: Every plugin here is pure ESM with no build step , so no prepare script runs at install time and pnpm never asks you to allowlist a build. That allowance is permission to execute a package's code on your machine, and none of these packages need it. House rules These hold for every package in this repository: - Public seams only. Plugins touch ctx.tools , ctx.llm , ctx.fs , ctx.attachments and friends — never harness internals. Installing one into a profile needs no change to the harness and no desktop rebuild. - No build step. Pure ESM, so the harness's own cordis instance is shared rat…
View full README on GitHub →Category
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)。
★ 2,208
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
★ 933
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.
★ 488