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

..

bench-vs-openclaw

test(bench): per-dispatch throughput — Minions vs OpenClaw --local

2026-04-18 08:24:17 +08:00

fixtures

GBrain v0.4.0 — production agent documentation + reference architecture (#10)

2026-04-09 10:17:13 -07:00

helpers.ts

test(e2e): Minions v7 concurrency + OpenClaw resilience coverage

2026-04-18 06:32:41 +08:00

mcp.test.ts

feat: GBrain v0.3.0 — contract-first architecture + ClawHub plugin (#7)

2026-04-08 23:26:11 -10:00

mechanical.test.ts

security: fix wave 3 — 9 vulns (file_upload, SSRF, recipe trust, prompt injection) (#174)

2026-04-16 23:03:15 -07:00

minions-concurrency.test.ts

test(e2e): Minions v7 concurrency + OpenClaw resilience coverage

2026-04-18 06:32:41 +08:00

minions-resilience.test.ts

test(e2e): Minions v7 concurrency + OpenClaw resilience coverage

2026-04-18 06:32:41 +08:00

search-quality.test.ts

feat: search quality boost — compiled truth ranking + detail parameter (v0.8.1) (#64)

2026-04-13 21:03:40 -10:00

skills.test.ts

docs: live sync setup + verification runbook + API key loading (#24)

2026-04-10 07:23:59 -10:00

sync.test.ts

feat: slugify file paths with spaces and special characters (v0.5.1) (#29)

2026-04-10 11:42:32 -07:00

upgrade.test.ts

feat: add gbrain check-update command and auto-update agent workflow (#15)

2026-04-09 12:25:04 -10:00