Benchmark matrix

Structural memory, measured against the baselines.

Exact-symbol lookup, graph recall, token economy, query latency, working set, index speed, and incremental freshness, kept in one reproducible benchmark matrix.

See pricingFor teams
97.3%trace accuracyright answer rate across 1K benchmark queries
13.4msavg traceRust-native graph traversal
83%context spared319K vs 1.91M token usage
1.5sindex window1,500 files, same benchmark machine

Research

Memtrace against the baselines.

The full public matrix shows where delay compounds: noisy chunks, stale indexes, missing graph recall, larger working sets, and 100x slower lookups.

memtrace-public/benchmarks
Best in rowDocumented tradeoff
Exact-symbol lookupmempalace, 1K queriesAcc@1 / precision@10fair/results_iso_1k_mempalace_*
Memtrace96.6% / 0.967best precision; -0.4 pp Acc@1
GitNexus97.0% / 0.702highest file-specific Acc@1
ChromaDB62.4% / 0.188chunk vectors trail exact symbols
CGC7.9% / 0.521shared-harness CGC row
Token economymempalace, same 1K queriesAcc@1 / 1k tokbenchmarks/README Bench #1
Memtrace495.52correct hits per 1k response tokens
GitNexus126.903.90x behind Memtrace
ChromaDB32.11large chunk payloads
CGC28.97low Acc@1 hurts token score
Exact-symbol lookupDjango, 1K queriesAcc@1 / precision@10fair/results_iso_1k_django_*
Memtrace79.7% / 0.807best precision; -1.4 pp Acc@1
GitNexus81.1% / 0.660highest file-specific Acc@1
ChromaDB34.2% / 0.128semantic chunks trail on symbols
CGCDNFDjango index did not finish
Query latencyDjango, 50K nodesAverage lookup latencyfair/results_iso_1k_django_*
Memtrace0.19 mssub-millisecond on Django
GitNexus20.47 ms108x slower
ChromaDB54.56 ms287x slower
CGCDNFDjango index did not finish
HEAD index speedDjango, 3.3K filesHEAD-only index timeBENCHMARKS-v0.3.22
Memtrace13.6 squeryable HEAD graph
GitNexus48.4 s3.6x slower
ChromaDB268.7 s19x slower
CGCDNF24+ min without progress
Working setDjango isolated processPeak RSSfair/results_iso_1k_django_*
Memtrace26.2 MBsmallest resident set
GitNexus30.9 MB1.18x larger
ChromaDB1133 MB43x larger
CGCDNFnot isolated on Django
Graph callersmempalace pyright GTFiltered callers recallbenchmarks/README Bench #3
Memtrace0.851highest callers recall
GitNexus0.013flow text rarely maps callers
ChromaDBN/Sgraph queries not supported
CGC0.584runner-up graph recall
Graph callersDjango pyright GTFiltered callers recallbenchmarks/README Bench #3
Memtrace0.816generalizes to larger corpus
GitNexus0.05315.4x behind Memtrace
ChromaDBN/Sgraph queries not supported
CGC0.000no Django caller recall
Incremental freshnessscratch fixture, 50 editsp95 time to queryablebenchmarks/README Bench #4
Memtrace42.5 mssub-50 ms freshness
GitNexusN/Sbatch-only eval-server
ChromaDB5001 mstimeout p95
CGC613.7 ms14.4x slower
Semantic intentDjango PR-title NL queriesRecall@10benchmarks/README Bench #2
Memtrace58.6%2nd on semantic workload
GitNexusN/Ano comparable recall row
ChromaDB66.8%semantic vector win
CGCN/Snot supported for NL retrieval

N/S means a benchmark method is not supported by that system. DNF means the published run did not finish under the documented benchmark conditions.