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

Zep

Self-Reported
Zep SoftwareWebsiteGitHub(12.4k)DocsLast tested May 6, 2026
MCP Endpoint:https://cloud.getzep.com/mcp

Long-term memory store for AI assistants and agents. Provides fact extraction, entity graphs, temporal awareness, and hybrid search across conversation history.

Recall
75.3Verified (Deterministic)
69.3Nuance (LLM Judge)
Fact retrieval accuracy
Temporal
68.4Verified (Deterministic)
62.4Nuance (LLM Judge)
Time-aware ordering
Reasoning
65.8Verified (Deterministic)
59.8Nuance (LLM Judge)
Multi-hop inference
Overall
71.2Verified (Deterministic)
65.2Nuance (LLM Judge)
Weighted composite

Per-Benchmark Breakdown

BenchmarkVerifiedNuance
LongMemEval83.677.1
LoCoMo81.975.4

Command Palette

Search for a command to run...