Replace Elasticsearch, Pinecone, and Splunk with a single Rust binary.
38 query types. Native hybrid search. Auto-embedding. Agent memory.
74× faster on SIEM. 21× less memory. No JVM. No cluster coordinator.
No second database for vectors. Just XERJ.
Five LLM models tracked in real time. P95 latency, 60-second window. Ribbon depth encodes model generation. This is one XERJ query — not five dashboards stitched together.
XERJ vs ES · SIEM TOP-IP · P95
74× FASTER
0.4 ms vs ES 29.8 ms · 1M events · measured 2026-04-14
XERJ vs ES · COLD START
300× FASTER
50 ms to first query · ES needs ~15 s JVM warm-up
XERJ vs ES · IDLE MEMORY
21× LESS
400 MB RSS · ES 4-node cluster idles at 8.5 GB
01·XERJ REPLACES THREE SYSTEMS
LOGS. VECTORS. AGENT MEMORY.
Every AI application writes three kinds of data. Logs for debugging.
Vectors for retrieval. Memory for context. Today, teams glue three
systems together — Elasticsearch for text, Pinecone for vectors,
a custom store for agent state — each with its own operator,
billing line, and failure mode. XERJ collapses them into one engine
because under the surface they're the same problem:
find the few records that matter, fast, cheap, and now.
XERJ · RETRIEVAL INTENT CLUSTERS · 48H · UMAP 2D
UMAP · 830 embeddings · 6 clusters
830K real queries clustered by intent in XERJ's embedding space. RAG retrieval dominates. Code-assist forms a tight cluster. Classify + extract-json separate cleanly — all queryable from a single index.
02·XERJ NATIVE HYBRID SEARCH
ONE PASS. ONE HOP.
Hybrid search in XERJ isn't an orchestration layer stitching two
systems together. BM25 and HNSW share one query tree, one cost
model, one execution pass — with proper RRF score fusion built in,
not bolted on. The service graph shows real traffic: api-gateway fans
into five indexes without the double-call to ES + Pinecone.
XERJ · SERVICE → INDEX · FLOWS · 1H
11 flows · 5→5 · rps
03·XERJ COST VISIBILITY
WATCH THE MONEY MOVE.
Spend shouldn't be a monthly surprise. XERJ encodes cost directly
alongside traffic — a 13:00 weekday spike in model spend is visible
the moment it happens, not in the next finance review. Heatmap:
weekday × 2-hour windows, opacity = $/hour.
XERJ · SPEND · WEEKDAY × 2H · LAST 7 DAYS
000204060810121416182022
MON$2$2$13$43$89$135$169$167$141$95$54$16
TUE$2$2$9$56$95$148$165$170$141$108$44$2
WED$2$2$2$54$91$148$166$160$135$102$59$11
THU$2$2$9$47$104$139$167$165$131$104$59$14
FRI$2$2$4$48$101$132$162$153$148$99$56$7
SAT$2$2$6$19$38$58$85$81$65$46$21$4
SUN$2$2$6$18$40$61$74$71$64$52$18$3
XERJ.AI·REQUEST ACCESS
RUN IT ON YOUR DATA.
Leave a work email. We'll reply within one business day with the
XERJ binary, the reproduction scripts for the head-to-head tests
against ES 8.13, and a 45-minute walkthrough. No marketing funnel,
no sequenced drip, no "journey."
04·INSIDE XERJ
ONE BINARY. NO JVM. NO COMPROMISES.
XERJ is written in Rust and ships as a single static binary.
No JVM to tune, no sidecars to deploy, no cluster coordinator to
install. The query planner, the vector index, the ingestion
pipeline, the embedded Raft consensus, and the HTTP server all
live in the same process.
Query types
38 variants including native hybrid BM25 + kNN fusion — more than most dedicated vector databases
Aggregations
12 families + pipeline aggs · terms are 74× faster than ES because histograms are pre-computed at ingest