Files
openswarm/backend/apps/agents
SirKentut a10617526a [pierre] feat: add __autopilot__ self-play bridge with slow-cadence agent supervision
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.
2026-06-25 19:32:17 -07:00
..
2026-03-13 12:09:25 -07:00