System Performance & Research

Evaluation metrics and performance characteristics extracted from the automated benchmarking suite.

Precision@5 Retrieval

Measures the accuracy of retrieving the top 5 most relevant memories for an LLM prompt context.

Kyros AI100%
Mem085%
Standard RAG62%

Average Query Latency

Query execution time (retrieving, scoring, and formatting facts) under concurrent workloads.

Kyros AI37.2ms
Mem0148.6ms
Standard RAG120.4ms

Token Consumption Efficiency

Token volume reduction compared to feeding raw conversation logs into the LLM context.

Kyros AI99.1% Reduction
Mem0Baseline
Standard RAG

Competitive Performance Analysis

Detailed benchmark comparing self-hosted Kyros AI against alternatives.

Evaluation DimensionKyros AI (Self-Hosted)Mem0Standard RAG
Precision@5 Retrieval100%85%62%
Average Query Latency37.2ms148.6ms120.4ms
Token Consumption Efficiency99.1% ReductionBaselineDynamic
Cryptographic Tamper ProtectionEnabled (Merkle + SHA)NoneNone
Biological-based Decay WeightsEnabled (Ebbinghaus)NoneNone
Context-Aware Causal GraphingEnabledNoneNone

Evaluation Methodology

Retrieval latency tests were conducted using concurrent requests over a PostgreSQL database with pgvector, caching active queries via Redis. Precision rates were computed using synthetic chatbot conversation datasets, evaluating whether the core factual statements (e.g. user profile attributes) were successfully retrieved in the top 5 results after injecting random conversational noise.