I'm Roman, maker of Wrangler. Before building it I was running five Claude Code / Codex sessions in parallel, and the thing that broke first wasn't the code - it was me: eleven tabs, an agent silently waiting 40 minutes for an approval, and no honest answer to "is this feature actually done?"
We launch here on Wednesday, and before that I'm genuinely curious where everyone else is on this curve:
Your agents say done — Wrangler proves it. The control tower for a fleet of coding agents: Claude Code, Codex, Cursor, 30+ more. Every session live in one place — even those started in a terminal — and blocked agents surface the moment they need you. Tickets, PRs, CI, and Slack reconciled into one honest board. It runs your tests, lint, and typecheck in the agent's worktree, so green means actually green. Review diffs, dispatch fixes in one click. Local-first, no account, free for macOS.
