Files
gbrain/test
Garry Tan 8633f9268e test(bench): per-dispatch throughput — Minions vs OpenClaw --local
20 serial dispatches each side, identical claude-haiku-4-5 call with the
same trivial prompt. p50/p95/p99 reported via statsFromResults. Serial
(not parallel) so the per-dispatch cost is measured honestly and LLM
token spend stays bounded (~$0.08 total).

Minions: one queue, one worker, one concurrency. Submit → poll to
completion before next submit. OpenClaw: N sequential
`openclaw agent --local` spawns.
2026-04-18 08:24:17 +08:00
..