protoctistmoses143/dsh-docs
protoctistmoses143★ 0TypeScript最后同步: 2026-08-15
Convert PDFs, Office docs, scanned images, and more to clean Markdown, JSON, or text locally with offline OCR—no servers, no API keys, fully private.
README 摘要
📄 dsh-docs - Read Any Document, Even Without Internet 🚀 Getting Started Welcome! This guide will help you download and run dsh-docs , a tool that lets you read, search, and understand documents like PDFs, Word files, images, and even scanned papers—all on your own computer, with no internet needed. Whether you want to turn a messy pile of scans into searchable text or just need to quickly read a tricky file format, this application does it for you. Think of it as a smart assistant that can "see" inside your files and pull out the words, even if they're pictures of text. It works quietly in the background, keeping your information private because nothing ever leaves your machine. ⚡ What Does This Do? You have files. You need answers. dsh-docs is a bridge between those files and you. It's a plugin designed for something called "DeepSeek Harness," which is a tool for working with AI assistants. But don't worry—you don't need to know anything about that. This app works independently to handle your documents. Here's the magic it performs: - Reads PDFs – Yes, even those ancient ones that won't let you copy text. - Reads Office Files – Word documents ( .docx ), Excel sheets ( .xlsx ), P…
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). | 全网第一个 DeepSeek Harness 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)。
★ 2,047
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
★ 920
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.
★ 457