gbrain

mirror of https://github.com/garrytan/gbrain.git synced 2026-07-28 14:59:47 +00:00

Files

T

Garry Tan 94713bb507 doc(benchmarks): Minions vs OpenClaw --local subagent dispatch

Real numbers on four claims: durability, throughput, fan-out, memory.
Same claude-haiku-4-5 call on both sides so the delta is queue+dispatch+
process cost on top of identical LLM work.

Headline: Minions rescues 10/10 from a SIGKILLed worker in 458ms while
OpenClaw --local loses all 10; ~10× faster per dispatch (778ms p50 vs
8086ms p50); ~21× faster at 10-wide fan-out AND 100% reliable vs OC's
43% failure rate; 2 MB vs 814 MB to keep 10 subagents in flight.

Honest caveats section covers what this doesn't test (OC gateway
multi-agent, load tests, other models). Fully reproducible via
test/e2e/bench-vs-openclaw/.

2026-04-18 08:33:45 +08:00

architecture

feat: GBrain v0.7.0 — Integration Recipes + SKILLPACK Breakout (#39 )

2026-04-10 23:39:06 -10:00

benchmarks

doc(benchmarks): Minions vs OpenClaw --local subagent dispatch

2026-04-18 08:33:45 +08:00

designs

feat: Minions v2 — agent orchestration primitives (pause/resume, inbox, tokens, replay)

2026-04-16 12:34:44 -07:00

ethos

feat: v0.9.0 -- smart file storage, publish, production-grade skills (#62 )