Show HN: SlimSnap – mark a screenshot element, get JSON for your coding agent

Category: other

Tags: ai-agents, screenshot, json-schema, productivity, developer-tools

Score: 7.0/10 (Innovation: 7, Technical: 6, Documentation: 8, Utility: 7)

SlimSnap defines an open, MIT-licensed JSON schema for converting screenshots into a structured text format (OCR'd elements, bounding boxes, annotations) that terminal-based AI coding agents can consume. It innovatively bridges the gap between visual UI understanding and text-only LLM interfaces, offering a pragmatic solution to a clear pain point for developers using agentic coding tools.

Target audience: backend devs, AI agent users, developers using CLI-based coding assistants

Repository: https://slimsnap.ai/ · MIT · 9 stars

View on Hacker News