My agent writes the code now. I built an IDE for the part that's left: reading it.

A developer built Reado, an MIT-licensed, local-first desktop IDE designed for reviewing code written by AI coding agents rather than typing it, where the primary action is leaving Markdown comments on specific lines that the agent resolves. The tool re-anchors comments when code moves, orphans comments whose code is deleted, and exposes an MCP server and CLI so agents can read tasks and mark them done themselves. The developer is seeking 50 developers who already use coding agents to test it on real code, offering 12 months of Reado Pro to the first 50 who send feedback.

A year ago most of my day was typing code. Today Claude Code types most of it, and my day is something else: reading what it wrote and deciding whether it stays. The tools didn't follow. Every editor I use is built around the cursor and the keyboard. And the way I talked to the agent about its code was worse: I'd spot something on line 212, switch to the terminal and type "in auth.ts, around the token refresh, the retry doesn't…", describing a location in prose to a machine that could have just been pointed at it. So I built Reado https://github.com/WatermelonBros/reado : a desktop IDE where the main thing you do is read, and the main action is leaving a comment on the exact lines that matter. Your agent resolves the comments. I call it inverted code review: you are the reviewer, the AI is the committer. Comments have to survive edits. When the agent rewrites a function, a comment pinned to "line 212" is now lying. Reado re-anchors comments when the code moves, and one whose code is gone becomes an orphan instead of pointing at the wrong line. Comments are plain Markdown in a .reado/ folder in your repo. Give the agent a contract, not a prompt. A small reado binary serves an MCP server and a CLI, so the agent reads the tasks and marks them done itself reado task done <id . The UI just watches the files. Let the agent propose, never decide. In a guided review the agent plans a route through a branch, riskiest files first, and its findings land on the line as proposals. Nothing is final until I approve it. That one rule is what made me trust it on real work. Reado is MIT, local-first, and runs on macOS, Linux and Windows. No account needed for the core loop: download it here https://github.com/WatermelonBros/reado/releases/latest . I'm looking for 50 developers who already work with a coding agent to use it on real code and tell me what breaks. The first 50 who send feedback get Reado Pro free for 12 months : reado.watermelon-studio.it/beta https://reado.watermelon-studio.it/beta . I'm the developer, so I'll answer every comment here.