Live · circle packing · your key

Run a search. Watch it pack.

Pick a scaffold — OpenEvolve, Top-K, or Best-of-N — point it at the circle-packing task with your own OpenRouter model and key, and press Run. The best-so-far curve climbs live, and every time the search beats its best valid packing the geometry is captured so you can scrub through how 26 circles rearrange to fill the square.

Configure

idle
Scaffold

MAP-Elites islands + adaptive explore/exploit selection (the open AlphaEvolve).

Model
OpenRouter API key

Sent only for this run; used in-process, never stored or logged.

Iterations30
1100
Seed

Enter a model and an API key.

Best Σ radii
of target
/ 2.635
Iteration
/ 30
Best-so-far
iter 0iter 30no trajectory yet
Run log

Run a search to stream the per-iteration log here.

Packing
run to see the packing
Following live

Each time the search beats its best valid packing, a frame is captured here.

01

Configure

Choose a scaffold, type an OpenRouter model id and your key, and set how many iterations to run — up to 100.

02

Run

Your chosen scaffold drives a real evolutionary loop on the bundled circle-packing task. Each candidate is scored in an isolated subprocess; results stream back as they land.

03

Watch it evolve

The best-so-far curve climbs toward the AlphaEvolve target. Scrub or replay the captured frames to see the packing rearrange — and open the solution code behind any frame.