The agent-readable web changes every week. Get woken only when it matters.
Reproducible · first edition 1 Sep 2026 · github.com/mrenzo20/ard-retrieval-benchmark

What do public ARD registries actually return?

Same queries, same day, every public registry that speaks the ARD spec's POST /search. Zero-dependency harness, one command, one JSON per edition. Published by Desvela, which competes in this table — its row is marked, and the method below is written to survive being read by a rival.

The table — 1 Sep 2026

RegistryLatency cold / warmTasks answeredDuplicatesGibberishSelf-retrieval
Desvela (ours)214 ms / 86 ms8/800 resultsn/a — own index
WellKnown HQ923 ms / 314 ms8/88 extra entries10 results, scored 51–564/5 at rank 1
Hugging Face Discover1853 ms / 1856 ms8/800 results0/5 — does not index us
Official MCP RegistryExcluded: does not speak ARD — 404 to the spec's request shape, serves its own /v0.1/search. Listed so it does not look like we picked convenient rivals

Medians of 5 samples. Cold = fresh connection per request, what a one-off agent call pays. Warm = keep-alive. Both published: our first harness version measured only warm and reported 307 ms for an endpoint curl timed at 1.16 s. Neither number lies; publishing only one means picking the convenient one.

The metric that matters most: gibberish

The negative control. xkqjvwz mplfrbn tzghdkw means nothing in any language. An honest registry returns zero results. A registry that returns ten results scored 51–56 has an undocumented noise floor — and once that is true, its relevance score cannot be used to decide anything, because a score of 55 might mean "match" or might mean "noise" and nothing in the response tells you which.

What this benchmark does not measure

Our own limits, declared

Reproduce it

git clone https://github.com/mrenzo20/ard-retrieval-benchmark
cd ard-retrieval-benchmark
node run.mjs      # Node ≥ 20, no dependencies, ~4 minutes

The query set, the registry roster with exclusions and reasons, and every edition's raw JSON live in the repo. If you re-run it and get different numbers, that is a finding — open an issue.