Watch a Governed Multi-Agent System Block, Verify, and Replay AI Code — Live

aming-claw — a system that lets AI agents write your code without you having to trust them. AI agents do all the implementation, but under enforced contracts: each task carries a route context (allowed/blocked actions, a file fence, required evidence), a gate physically refuses any write outside it, a separate observer reviews instead of implementing, and every step lands in a replayable timeline.

This is a live demo, not slides. I’ll show the real running system: a worker attempting an out-of-fence write and the gate returning a hard 422; a task refused at close because it has no timeline evidence; multiple commit-bound workers running in parallel from a single prompt; and the timeline replayed afterward. To make it concrete, I’m running it on a real product I’m currently building — an AI video-generation tool (auto-script + voice from on-screen content) — so you watch one prompt fan out to parallel AI workers and land an actual commit of a real codebase.