Vision / OCR
Plugins that read, parse, recognize and analyze images, screenshots and PDFs — giving text-only agents the ability to see.
Artifacts
Sorted by trust, then stars · search & paginate below

open-design
@nexu-io
🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen & 20+ CLIs via BYOK.

modlens
@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).

PicGo-Core
@PicGo
:zap:The ultimate image uploading engine. Both CLI & API supports.

agent-vision-toolkit
@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

dsh-ads
@Nagi-ovo
是兄弟就来蹬我!DSH Web UI 广告:2005 年中文站点风格的侧栏广告 / 对话内信息流 / 角落弹窗 + 一个真实热区比视觉小得多的关闭叉。素材全虚构,域名打码。

dsh-vision-toolkit
@Anionex
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.

dsh-handbook
@Electricitysheep
DeepSeek Harness (dsh) 从 0 到 1 深度手册:安装/插件开发/性能调优/同模型多 Agent 实测对比(中文 + 英文 PDF)

notes
@zhaoolee
开源版锤子便签,复刻锤科美学,一键Docker私有化部署,支持skill调用,支持dsh plugin,支持多租户,一键生成公众号格式,支持导出便签为图片

dsh-browser
@Lum1104
dsh plugin: Chrome sidebar extension that lets DSH operate your browser directly—no vision capabilities required.

Deepseek-Harness-Desktop
@ChisaAlter
Electron desktop shell for DeepSeek Harness web UI

dsh-vision-router
@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.

atlas-cloud-skills
@AtlasCloudAI
Atlas Cloud skills for Claude Code, Codex & Gemini CLI — generate images/videos and call 300+ AI models from your coding agent.

dsh-vision
@william-jin-cmu
dsh 插件:给纯文本 DeepSeek 加视觉——view_image 工具桥接任意 OpenAI 兼容 VLM(默认智谱免费档,实测 4 厂商 10 模型)

dsh-computer-use
@Anionex
为 DeepSeek Harness 提供电脑控制插件:新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入(目前支持macos)|Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.

dsh-vision
@oil-oil
Near-native image understanding for DeepSeek Harness

dsh-group-photo
@SenmuuuuW
DSH 内测收官合影墙:GitHub OAuth 零权限登录 + 冻结白名单校验的拍立得合影站(含 DSH Skill 包装)

dsh-web-review
@CanglongCl
DeepSeek Harness Web GUI 的网页预览与元素批注插件,让 AI 根据可视化反馈直接修改前端源码。

ego-browser
@Fisfzy
DSH(DeepSeek Harness)插件:把 ego-lite 浏览器(给 AI Agent 用的 Chromium)接入 HARNESS——13 个结构化 ego_* 工具(文本语义快照、语义定位点击、表单填充、截图、CDP 控制、任务空间隔离),内置 ego 运行时,Linux + Chrome 开箱即用,无需克隆官方仓库或手动构建。