mirror of
https://github.com/openswarm-ai/openswarm.git
synced 2026-09-28 12:34:50 +02:00
Two-loop design for fast-twitch apps (Flappy, Doodle Jump) the agent cannot react to frame-by-frame over the network: the bridge runs policy() at frame rate as the reflex (inner loop), while the supervisor steers on a slow cadence via getState and __autopilot__ knobs (outer loop). Wires this through the webapp_template bridge, the shell-injected bridge in main.js, and the APP system prompt. Also deny the 'fullscreen' permission so a preview webview's HTML5 fullscreen no longer hijacks the whole OpenSwarm window.