Public benchmark

Measured on real memory tasks with two checks

Engram is measured two ways: first, whether it retrieves the right evidence; second, whether an LLM can answer correctly from that retrieved context.

We keep retrieval and answer accuracy separate. Both use public LoCoMo, but they measure different parts of the memory loop.

1,536
scored evidence-retrieval questions
92.19%
Engram R@50
66.33%
answer accuracy from top-50 context
+8.21pp
R@50 lead over LangMem

LoCoMo evidence retrieval

Full public run. Scores show whether the required source evidence appears in the retrieved memories.

+8.21pp over next best R@50N=1,536
SystemMRRR@1R@50R@200
Engram0.534540.63%92.19%97.66%
LangMem / LangGraph0.400228.32%83.98%94.53%
Mem0 OSS0.399928.32%83.92%94.27%
AgentMemory0.427033.20%79.10%84.96%
BM250.467634.57%78.19%85.74%

LoCoMo answer-level judge

Codex/self-reviewed diagnostic on the same 98 tasks. Scores show whether the generated answer is correct from retrieved context.

N=98
SystemTop-50 answerTop-200 answervs base model
Engram66.33%59.18%+56.13pp
Session-file BM2561.22%53.06%+51.02pp
Mem0 OSS55.10%57.14%+44.90pp
BM2548.98%44.90%+38.78pp
LangMem / LangGraph46.94%52.04%+36.74pp
No memory10.20%9.18%baseline
?

How to read R@200 and Top-200

Evidence retrieval is cumulative: R@200 can include everything R@50 found plus more, so it should not be lower. Answer accuracy is different. More retrieved context can also add noise or conflicting memories, so Top-50 may answer cleaner while Top-200 tests whether packaging stays useful with more evidence.

Support Loop

Help us make Engram sharper

If setup is confusing, a tool behaves strangely, or a pricing limit feels wrong, send it here. The message lands directly with us.

Feedback

Tell us what is missing

Bugs, confusing setup steps, pricing questions, and product ideas go straight to the Engram team.

10 more characters needed0/10