#screenshot
GitHub Topic「screenshot」がついているAI関連リポジトリの集計。Topicはリポジトリ作者が自己申告するメタタグで、AI関連の文脈で何が「screenshot」と分類されているかを可視化します。
REPOS #screenshot のRepo (TOP 9 / Stars降順)
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.
sfyyy/dsh-vision-bridgeOn-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
JunchenMeteor/AgentShotLocal-first screenshot bridge for Claude Code, Codex CLI, Aider, Gemini CLI, OpenCode, and terminal AI agents.
WANGJIEYI/clipboard-image-to-pathConvert Windows clipboard images to file paths so text-only AI agents (Claude Code, Codex, Cursor...) can read screenshots - AutoHotkey v2
yygg693/autocomputerAI-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.
usagi20/claude-code-vision-skillGive Claude Code image understanding when its primary model cannot see images. Supports UI screenshots, photos, documents, charts, comparisons, and Windows clipboard input through Qwen.
timurarslanov94/yoinkCopy any UI element from any website — HTML, CSS, Tailwind, JSX, fonts, screenshots — bundled and ready to paste into Claude or ChatGPT. 100% free.
Thedan-1/ScreenQA-ocr-quiz-solver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
pixelvault-dev/desktopCopy an image, paste a hosted URL — a macOS/Linux menubar app for feeding images to cloud coding agents. By PixelVault.
RELATED 他のTopicも見る · 全Topicランキング →
#claude-code
1,555#ai-agents
1,156#llm
1,066#claude
936#python
802#ai
737#developer-tools
723#mcp
719#codex
517集計対象: 各Repoの最新contentスナップショットの topics_json に小文字一致でマッチしたもの。 算出方法