AI News HubLIVE
In-site rewrite2 min read

Show HN: Remarc – comment on anything on your screen and send it to your agent

Your browser does not support the video tag. Download for macOS View on GitHub FREE and Open Source · Requires macOS 14.0 or later Why I made Remarc As a detail-obsessed designer who now builds daily with AI, fee…

SourceHacker News AIAuthor: young_mete

Your browser does not support the video tag. Download for macOS View on GitHub FREE and Open Source · Requires macOS 14.0 or later Why I made Remarc As a detail-obsessed designer who now builds daily with AI, feedback is a core part of my creative process. AI made it incredibly easy to get from zero to 90%, but it’s the last 10% that sets your product apart from the pack. The unglamorous reality is that most of the 10% is rigorous QA, feedback, and iteration. Remarc is made for this last 10%. It removes friction to providing structured, contextual, and detailed feedback to your AI agents. My hope is that it helps others craft better products. - Mete Frequently Asked Questions What is Remarc? Remarc is a contextual feedback layer for AI agents. It lives in your menu bar and lets you leave comments, screenshots, and voice critiques on anything on your screen - then your AI agent sees it all with full context via MCP. It's the missing input channel between you and your agent. How much does Remarc cost? Remarc is free and open source under the MIT license. There are no accounts, no subscriptions, and no paid tiers - just download it and start commenting. If you find it useful, starring the GitHub repository helps more people discover it. Which coding agents does it work with? Claude Code and Codex connect through the Remarc plugin, and Cursor is set up directly from the app's preferences. Under the hood it's all MCP, so any agent that supports MCP can read your comments, work through them, and mark them resolved. Why not just type everything into my agent's chat? Describing what you see is slow and lossy. Remarc captures the thing itself - the selected text, the source app, the screenshot region, the web element - along with your comment, so your agent works from structured context instead of a paraphrase. It's the difference between writing a bug report and pointing at the bug. Is my data private? Yes. Remarc stores your comments in a local file on your Mac and has no accounts, telemetry, or cloud backend for comments. Data leaves only through agents or integrations you explicitly use; voice transcription runs on-device. How do I get the Chrome extension? The Remarc Chrome extension lets you leave comments directly on web pages and automatically attaches web context - like the page URL, selected text, and surrounding content - so your AI agent has the full picture. Since it's not on the Chrome Web Store yet, you'll need to install it manually - it only takes a minute. Head to the Chrome extension page for the download and setup instructions. Where can I learn more? The documentation covers setup, agent integrations, and every feature in detail. The GitHub repository has the source code and release notes. How do I provide feedback? Found a bug or have an idea? Open an issue on GitHub, or reach out via email, on X, or on Threads.