PROJECT TOPICS
INSTALL REFERENCE
dsh plugin --profile web add github:RailgunHamster/dsh-web-search
该命令指向仓库当前默认分支；尚无绑定当前 commit 的完整验证结果。
PROJECT README
Host and Web client plugin for selecting and routing DeepSeek Harness web_search
backends.
The Host half registers one ctx.web provider named dsh-web-search-selected. Its
persisted web-search setting selects either Niumacode GPT-5.6 Luna native web search
or DeepSeek native web search. Luna is one backend, not the plugin identity. The Web
client adds a dedicated Web search settings section and saves the selection through
the Host settings scope.
Deployment instructions: DEPLOY.md.
中文文档：README.zh-CN.md.
CLASSIFICATION EVIDENCE
系统优先读取 GitHub Topics，再与站内分类词典和词根规则比对。当前命中： web-search。
liustack
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）。
Anionex
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
ysr666
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.