Regent
Version control for AI coding agents — audit, undo, and replay every session.
Visit website →About
Regent brings version control to AI coding agents. Where Git tracks file changes, Regent tracks agent actions — every prompt, every edit, every decision — stored in a .regent/ directory alongside your code.
Each conversation gets its own branch. You can undo specific agent changes, trace which prompt caused a particular line to appear, replay past sessions, and run multiple agents in parallel without conflicts.
Regent works with Claude Code, Codex, and OpenCode out of the box. It is free and open-source under the Apache 2.0 license, currently in public alpha.