Architect
A strong model plans; a cheap one writes the code.
A single model is one agent in a loop. A mix wires several over one workspace - a planner, an implementer, a critic, a judge. lemon-squeezer runs the first four of these as scored harnesses on the same evals as everything else; the fifth, Swarm, is shown for shape (it is how this very page was built, not a benchmark arm). Below: how each is wired, and what it buys.
A strong model plans; a cheap one writes the code.
Draft, get reviewed, refine - on a loop.
Several models each draft; a judge picks the best.
Write code and its tests, then self-correct until they pass.
Many agents build disjoint parts in parallel; a conductor integrates.
Loading runs...
Claude Code conductor ยท claude-opus-4.8
planned the work, wrote the page, integrated the pieces, verified the build
kimi (via squeezer)
kimi-k2.7-code โcloudthe orchestration patterns data (JSON)
$0.011 ยท 23k/2.7k tok
Three agents in parallel: ~1.1c of metered API for the two paid legs (kimi + aider); codex ran on a ChatGPT subscription and Claude was the conductor. Run concurrently, so wall-clock was the slowest single leg, not the sum.
This tab was built by one Claude conducting codex, kimi, and aider in parallel - the same idea as the mixes above, one level up. Writeup: nanlives.com.