Analytics

Live, public usage data for Agent402. Every tool call records four aggregate fields after responding - slug, latency, cache flag, error flag - with no PII. Window: 1h.

1h 24h 7d 30d

Showing all calls (incl. synthetic test traffic). Hide synthetic

Showing probe calls (empty-input scans). Hide probes

Tool calls (1h)

308

across the whole catalog

Cache hit rate

24.4%

served from Redis without re-fetching upstream

Schema mismatches (4xx)

0.0%

input we didn't accept - caller gets back the schema + an example

Server errors (5xx)

0.0%

handler or upstream failure - actionable

Latency p50 / p95

140 ms / 1.85 s

avg 542 ms

Peak hour

2026-09-16 13:00Z

292 calls

Tool calls per hour (last 1h)

Live, write-through from the dispatcher - every tool call is recorded after responding (no PII, no caller wallet, no IP).

Top tools by volume (last 1h)

Click a slug to see the tool's docs page.

#	Tool	Cache %	4xx %	5xx %	p50	p95
1	_find	39.8%	0.0%	0.0%	100 ms	1.59 s
2	_route	7.6%	0.0%	0.0%	897 ms	2.30 s
3	base64	0.0%	0.0%	0.0%	-	1 ms
4	hash	0.0%	0.0%	0.0%	1 ms	2 ms
5	unit-convert	0.0%	0.0%	0.0%	-	-
6	uuid	0.0%	0.0%	0.0%	1 ms	1 ms

Top error slugs (last 1h)

Tools ranked by total errored calls. 4xx = caller sent the wrong shape (often a schema-coverage gap we can fix with input aliases). 5xx = handler or upstream broke (the actionable one).

#	Tool	Calls	4xx	5xx	Errors	Error %
No errors in the last 1h - every tool call returned 2xx.

What's recorded

Privacy-by-default: aggregate counters only.

Each tool call records five fields after responding: slug, latency_ms, cached (Redis hit), errored, and the HTTP status (so 4xx caller errors and 5xx handler/upstream failures can be told apart). No caller identity, wallet, payment, input, output, or IP is logged. The dashboard reflects exactly what's in the table.

curl -s https://agent402.tools/api/analytics?hours=24&top=25

Analytics is open-source - part of Agent402. Self-hosters get the same dashboard by attaching a Postgres instance.