mem0ai/memory-benchmarks

Agent Memory Benchmark

Unified benchmark for evaluating conversational memory and RAG across multiple datasets

Evaluation framework for benchmarking memory systems.

HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.

Code for MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems

A Unified Memory Benchmark Suite for Memory-Augmented Agents

GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.

Structured registry of agent memory benchmarks, with every field traced to its source