StyloBot benchmarks
StyloBot runs up to 57 detectors in a wave-gated pipeline. A request only pays for the work its evidence needs, while the full measurement record stays public.
These figures describe recorded test runs, not a capacity promise. Hardware, upstream behavior, traffic shape, persistence, and enforcement policy all change the result.
Recorded end-to-end soak
The 31 May 2026 performance pass used the win-x64 AOT gateway with detection enabled, an asynchronous Kestrel upstream, and a one-hour soak targeted at 50 RPS. It completed 150,669 requests at 38.6 actual RPS.
The first five seconds included warm-up EOFs. The report records 1.25% errors, mostly from that warm-up window, plus a 150–220 MB steady memory band.
What we measure
- BenchmarkDotNet: in-process detector and pipeline work, allocations, and regression thresholds.
- k6 soak tests: end-to-end gateway throughput, latency, connections, persistence, and enforcement under load.
- Unit and integration suites: correctness and behavior across the same FOSS and commercial paths customers run.
Read the full context
The repository includes the benchmark harness, scenarios, raw BenchmarkDotNet artifacts, k6 scripts, command lines, hardware notes, and known limits. Use those details when comparing a run with your own deployment.
Benchmark harness →Performance without a usage-meter surprise
FOSS is free and easy to run. Commercial licences fund the project and add manageability, reporting, and advanced features. Neither option turns requests, seats, bandwidth, or a DDoS into a StyloBot usage bill.