Comparison | Mem0

Sibyl vs Mem0: Scale365, 191k records and extraction cost

Why Mem0 is tested with infer=False, what that measures, and what enabling inference would cost.

Full test note

The Mem0 story is really about cost, not a dunk. The local baseline I tested is real and reproducible, and limited on purpose. A stronger Mem0 mode exists, but the reports put a price tag on it: extraction stops being a footnote once the corpus hits 41M tokens.

Read the full test page
Sibyl retrieval350/350
Mem0 retrieval92/350
Mem0 answers105/350
Mem0 avg context1,720 tokens
Mem0 ingestion5,512 s
Mem0 answer cost$2.76

Verdict

Mem0 retrieves 92/350 and reaches 105/350 after Sonnet, with 1,720 average context tokens and about 92 minutes of ingestion.

Mem0 is tested with local Qdrant, fastembed, BM25 sparse and `infer=False`. The test measures a local baseline without LLM extraction, not Mem0 in its smartest configuration.

Comparison table

MetricSibylMem0
Retrieval350/35092/350
Sonnet answers344/350105/350
Average context228 tokens1,720 tokens
Ingestion48 s5,512 s
Estimated answer cost$0.64$2.76

Methodological caveat

Mem0 is not tested with `infer=True`. That is an explicit choice: enabling LLM extraction on this corpus would introduce major cost and ingestion time into the benchmark.

Why not the best possible configuration?

Rerun the test

python scripts/run_mem0_365d_500c_category_baseline.py

Evidence files