#screenshot

Eyes for AI coding agents 👁️ — render → perceive → report → fix → re-render. A machine-graded visual feedback loop (DOM/contrast/OCR-grounded + optional vision LLM) agents consume to self-correct before claiming done.

On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

给纯文本大模型装上原生视觉：流式真实思考链 · 跨轮次无感重看 · 像素级证据与 SVG 图元 · OpenAI/Anthropic/Responses 三协议兼容 | Native vision for text-only LLMs: streaming real thinking chain, cross-turn re-view, pixel-level evidence & SVG primitives, OpenAI/Anthropic/Responses compatible.

Copy an image, paste a hosted URL — a macOS/Linux menubar app for feeding images to cloud coding agents. By PixelVault.

屏幕区域 OCR + 大模型自动答题助手 | Screen-region OCR + LLM quiz solver — 框住题目区域，内容一变自动截图、本地 OCR、大模型作答。支持 DeepSeek 等 OpenAI 兼容接口与多模态视觉模型

Local-first screenshot bridge for Claude Code, Codex CLI, Aider, Gemini CLI, OpenCode, and terminal AI agents.

DeepSeek 网页版视觉 MCP / DeepSeek Web Vision MCP: 为 Claude Code / OpenCode / Codex 等提供本地图片分析、批量截图审查与 Windows 自主截图 (unofficial reverse-engineered, for learning only)

Convert Windows clipboard images to file paths so text-only AI agents (Claude Code, Codex, Cursor...) can read screenshots - AutoHotkey v2

👁️ /screenshot — real Chrome screenshots for your coding agent. A Claude Code plugin: 3 skills, a visual-reviewer agent and a bundled MCP camera.

Tirou print no Windows, o Ctrl+V vira o caminho do arquivo + uma descrição feita por IA (Claude ou Ollama local).

Send screenshots and files to Claude Code / Codex CLI running on a remote Linux server — upload in the browser, copy the path, paste to the agent. npx / uvx, HTTPS, zero deps. 在远程 Linux 上用 Claude Code、Codex CLI 时，把截图和文件从浏览器传给 AI agent，并下载结果。

AI-driven desktop GUI automation — Rust core + Python SDK + MCP Server + HTML5 Dashboard. Zero-build Obsidian UI with jelly physics, desktop console, RPA recorder, SQLite audit.

Give Claude Code image understanding when its primary model cannot see images. Supports UI screenshots, photos, documents, charts, comparisons, and Windows clipboard input through Qwen.

Copy any UI element from any website — HTML, CSS, Tailwind, JSX, fonts, screenshots — bundled and ready to paste into Claude or ChatGPT. 100% free.

Turn annotated screenshots into AI-ready context.

AI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your terminal.

Mark up a screenshot in a Paint-style editor and attach it to your next message in Claude Code