AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
Rust agent-memoryai-agentsbm25claude-codeclicode-searchcursordatabaseelasticsearchfull-text-searchhybrid-searchjsonllocal-firstmcpmcp-servermodel-context-protocolragrustsearch-enginevector-search
title: "What does the XERJ benchmark board say?" evidence:
- claim: "Board generated by bench-matrix.mjs" source: "demo/playbooks/SCORECARD.md" expect: [FC-NUM-COMPANION, FC-NUM-UNKNOWN]
What does the XERJ benchmark board say?
XERJ ingests 1.72× faster than Elasticsearch 8.13.4 and its index is 1.61× smaller on disk.
kNN search at k=10 comes in at 1.18× on the same board.
Our internal runs also showed 7.3× on filtered aggregations and a 44% drop in p95 latency.