agentgateway history
Aug 2026 → Nov 2026
openai → openai cell. The engine changed between these runs (f3adbb1 → d240bad), so differences can include instrument changes, not only gateway changes. Changes within ±5% show as roughly unchanged (—); this is a display tolerance, not a statistical margin.
| Reading | Aug 2026 | Nov 2026 | Change | Rank Aug 2026 → Nov 2026 |
|---|---|---|---|---|
| Added latency p50 (µs) | 195 µs | 216 µs | ↓ +10.8% | 4 of 14 → 5 of 15 |
| Added latency p99 (µs) | 235 µs | 251 µs | ↓ +6.8% | 4 of 14 → 3 of 15 |
| Throughput, p99 ≤ 1 ms (req/s) | 23,156 req/s | 21,156 req/s | ↓ -8.6% | 1 of 3 → 1 of 2 |
| Throughput, p99 ≤ 5 ms (req/s) | 24,672 req/s | 22,239 req/s | ↓ -9.9% | 4 of 4 → 2 of 2 |
| Throughput, p99 ≤ 10 ms (req/s) | 24,672 req/s | 22,380 req/s | ↓ -9.3% | 4 of 5 → 3 of 3 |
| Throughput, p99 unbounded (req/s) | 24,672 req/s | 22,545 req/s | ↓ -8.6% | 3 of 5 → 2 of 2 |
| CPU per request (µs) | 168.2 | 188.6 | ↓ +12.1% | 3 of 14 → 4 of 14 |
| Idle RSS (MiB) | 24.84 MiB | 34 MiB | ↓ +36.9% | — → — |
| Peak RSS (MiB) | 47.42 MiB | 54.52 MiB | ↓ +15.0% | — → — |
Runs
2 published runs · Added latency p99 (µs), openai → openai · values describe the recorded local-mock configuration; a missing reading is never zero. Hover a trend for its comparability details.
| Measured | Build | Engine | Result | Trend | Field placement | Evidence |
|---|---|---|---|---|---|---|
| ghcr.io/agentgateway/agentgateway:v1.7.0 | d240bad | 251 µs | Engine changed | 3 of 15 Current field | Run evidence | |
| ghcr.io/agentgateway/agentgateway:v1.4.1 | f3adbb1 | 235 µs | First run | 4 of 14 Aug 2026 field | Run evidence |