B'
Bench'd
langchain-memory 0.0 on LongMemEvalcognee 0.0 on LongMemEvalmem0-local 0.0 on LongMemEvalllamaindex-memory 0.0 on LongMemEvalllm-baseline 0.0 on LongMemEvalverifiedstate 0.0 on LongMemEvallangchain-memory 0.0 on LongMemEvalLetta 88.4 on LongMemEval3 systems independently scored36 systems indexedlangchain-memory 0.0 on LongMemEvalcognee 0.0 on LongMemEvalmem0-local 0.0 on LongMemEvalllamaindex-memory 0.0 on LongMemEvalllm-baseline 0.0 on LongMemEvalverifiedstate 0.0 on LongMemEvallangchain-memory 0.0 on LongMemEvalLetta 88.4 on LongMemEval3 systems independently scored36 systems indexed

Mastra

Self-Reported
Mastra AIWebsiteGitHub(9.8k)DocsLast tested May 4, 2026
MCP Endpoint:https://memory.mastra.ai/mcp

TypeScript-native AI agent framework with integrated memory, RAG, and workflow orchestration. Offers pluggable memory backends and first-class MCP support for building production agents.

Recall
84.7Verified (Deterministic)
78.7Nuance (LLM Judge)
Fact retrieval accuracy
Temporal
85.8Verified (Deterministic)
79.8Nuance (LLM Judge)
Time-aware ordering
Reasoning
78.9Verified (Deterministic)
72.9Nuance (LLM Judge)
Multi-hop inference
Overall
84.2Verified (Deterministic)
78.2Nuance (LLM Judge)
Weighted composite

Per-Benchmark Breakdown

BenchmarkVerifiedNuance
LoCoMo82.475.9
PersonaMem81.574.9

Command Palette

Search for a command to run...