Skip to content

Benchmarks

Every number here names the conditions it was measured under. Where a result is a tie, it is reported as a tie.

Benchmark: Token Savings vs File-Based Memory

Section titled “Benchmark: Token Savings vs File-Based Memory”

Benchmarked with 15 diverse queries across 4 scales. File-based memory (CLAUDE.md, memory files) loads everything into context every conversation. YantrikDB’s selective recall retrieves only the 3–5 memories relevant to the current task.

MemoriesFile-BasedYantrikDBSavingsPrecision
1001,770 tokens69 tokens96%66%
5009,807 tokens72 tokens99.3%77%
1,00019,988 tokens72 tokens99.6%84%
5,000101,739 tokens53 tokens99.9%88%

Selective recall cost is O(1). File-based memory cost is O(n).

At 1,000 memories, file-based memory is about 20K tokens; at 5,000 it is about 102K, exceeding 32K and 100K context windows. YantrikDB stays at ~70 tokens per query with recall latency under 60ms. Precision improves with more data: the opposite of file-based memory, which degrades as context fills up.

Works with Claude Code, Codex, Cursor, Windsurf, Copilot, Kilo Code — any MCP-compatible agent. Run the benchmark yourself: python benchmarks/bench_token_savings.py