wubbery://games — frame time, input latency and the fight they decide
Sixteen milliseconds is the whole budget. You get it back.
Every fight is decided by milliseconds nobody can see: who rounds the corner first, whether the server believed the shot, whether the crosshair was still on the target one frame later. A 60 fps frame is 16.6 ms and everything a game works out has to fit inside it alongside the rendering. You get that time back — no stutter, no hitch, no character that thinks for a moment. And it refuses the budgets that cannot be met at any quality setting, before a build ships into them.
0.01%Of a 60 fps frame spent on one request, at 1.856–1.926 µs on a Google Cloud c3-standard-8
6/6Framerate targets refused as unreachable at ANY quality setting, before the build ships
+30.3%Frame cost brought inside a 60 fps budget with the picture held
Watch it hold the frame
Same scene, one clock. Left, everything at full detail: when seventy extra balls flood in it goes over budget and every other frame is dropped, so the balls stutter. Right, the governor turns the grey clutter down and leaves the hero balls untouched, so it stays smooth. A rendered demonstration of the engine’s real behaviour; a dropped frame is shown the way one actually looks — the previous image again.
Play with it
Same cursor, two fields. Move over either one. The left answers the long way round; the right answers in the frame. Then drop some balls.
THE LONG WAY ROUNDANSWERED IN THE FRAME
DROP A BALL · click or tap
What actually binds
Xbox
PlayStation
PC and Steam
Measured, on a named alternative
Guards are reported blocked-of-attempted, never as a percentage — “zero violations” without the attempt count is a claim about nothing. Each is posed against a case that passes the check the industry already runs, because a guard that only catches obvious mistakes measures nothing.
Checked on this workload
8 measured checks run here, of which 6 refuse a target outright rather than degrade toward it. You see every one of them, against your own traffic, in a proof of concept.
29 of 29 blocked
Forty-eight more are measured for games and live ops — shots that did not register, the duel that was decided before you could answer it, footsteps nobody could hear, input latency end to end, matchmaking, handhelds, netcode feel, patches, installs, launch nights, cross-play fairness. They surface in a proof of concept, against your numbers.
What it moves for you — WUBBERY off, then on
Every pair below is the same measurement with WUBBERY switched off and then on, under the condition printed beside it. Your own traffic replaces the population in the shadow run.
80.65% composed · quality held 89.5 / 86.6 / 86.5 — the 60 fps budget IS 16.67 ms
Without us the worst frames miss the budget by 41%. With us they land exactly on it.
What it means for you
This is the same measurement, WUBBERY off and then on. The only way to know what it does on your traffic is to watch it there: a free shadow run serves everything exactly as you do today and shows both columns, live, for you. Nothing replaced, nothing bought, nothing owed unless it wins.
The difference between a control that feels attached and one that feels remote.
What it means for you
This is the same measurement, WUBBERY off and then on. The only way to know what it does on your traffic is to watch it there: a free shadow run serves everything exactly as you do today and shows both columns, live, for you. Nothing replaced, nothing bought, nothing owed unless it wins.
Free and read-only. It runs beside your system on your real traffic, and nothing changes until you say so.
What we will not claim: these figures are measured on seeded workloads on our reference machine, not on a console or a shipped title — your numbers will differ, and every module states its own boundary in its output. This is not a profiler and makes no claim about a game we have not run against.
Figures measured at seed 1 on the WUBBERY engine and reproducible with the command above. WUBBERY is independent; company and product names are used for identification only and imply no endorsement.
