Benchmarks
| Benchmark | Description | Source | Categories |
|---|---|---|---|
| LoCoMo | Long context memory testing fact recall across extended conversations | snap-research/locomo | single-hop, multi-hop, temporal, world-knowledge, adversarial |
| LongMemEval | Long-term memory evaluation across multiple sessions with knowledge updates | xiaowu0162/longmemeval | single-session-user, single-session-assistant, multi-session, temporal-reasoning, knowledge-update |
| ConvoMem | Conversational memory focused on personalization and preference learning | Salesforce/ConvoMem | user_evidence, assistant_facts_evidence, preference_evidence, changing_evidence, abstention_evidence |
We’re actively adding support for more benchmarks. Contribute your own or create a feature request.
Providers
Supermemory
Chunk-based semantic search
Mem0
LLM-powered memory extraction
Zep
Knowledge graph construction
We’re actively adding support for more providers. Contribute your own or create a feature request.