AInotate gives AI agents annotated screenshots. Ask an agent where a setting is and it captures the page or window, finds the elements by text or role, and draws numbered steps, Skitch-style arrows, boxes and labels placed where they cover the least content. Emails, tokens and other secrets are redacted automatically, and the agent checks a preview before it sends the image. Use it for "where do I click" answers, bug reports, how-to guides and before/after shots of a change. It runs locally as an MCP server, a CLI and an agent skill, with plugins for Claude Code, Codex, Gemini CLI and Cursor. Free and open source.