ann-benchmarks
reference corpus · status live · domain DB (Databases and storage engines) · lane A · refresh pinned · tags GLOBAL · VECTOR-SEARCH · BENCHMARKING · RECALL · METHODOLOGY · PYTHON
What an agent uses it for
An agent working on measuring ANN recall-vs-latency and comparing vector indexes queries this for ann-benchmarks' datasets, recall methodology and runner harness.
curl -fsSLO https://raw.githubusercontent.com/xerj-org/xerj/corpus-hub/tools/xerj-code/hub/ann-benchmarks.jsonxerj corpus add --from ./ann-benchmarks.jsonxerj corpus index ann-benchmarks then xerj code ann-benchmarks "your question"Needs the xerj CLI and a local node running; the copy prompt covers both, checks each step, and shows how to stop only the node you started. No shell: the MCP tool xerj_code_search with corpus: "ann-benchmarks", once the corpus is indexed on the node.
Sources and pins
| source | pin | licence | size | review note |
|---|---|---|---|---|
| ann-benchmarks | 2e081ad32c1e | MIT | 2.6 MB / 208 files | licence host-verified (ok-spdx): MIT |
2.6 MB across 208 files. Added 2026-10-13.
Rights
MIT. Redistribution permitted with attribution per the licence review. The review block records a human opening each licence file at the pin. Detector output is a hint, never the verdict.
Retrieval spot-check (G7)
Not yet spot-checked. Queries are pre-registered in the registry before grading.