Line the designs up and the variable is not where facts sit, it is where the ruling on truth happens, or whether one happens at all. In LangChain's `ConversationKGMemory` it happens nowhere: triples go in, a contradicting triple goes in beside it, and retrieval has no basis for preferring either [6]. In Mem0 it happens on write, as a second model call that compares each extracted candidate against what is already stored and returns ADD, UPDATE, DELETE or NOOP [7]. In Zep it happens at query time, because edges carry both event time and ingestion time and superseded facts are flagged invalid rather than removed, which is how the graph can still answer where someone worked in 2023 after they have changed jobs [11][12].
That gives you the price list. A top-k recall loop spends no model calls deciding what remains true, which is exactly why it repeats the corrected answer [1][2]; Mem0 spends two per ingested message, one to extract and one to adjudicate [7], so the reconciliation design carries an extra model call per message over the retrieval-only baseline [1]. The author is direct about where that lands: an extra hop with extra cost and latency on the write path, plus the failure mode of an over-eager extraction prompt producing hundreds of low-value facts that dilute retrieval [10]. Writes are async by default [9], which moves the latency off the response path without moving the spend.
The worst arithmetic in the piece belongs to the option that looks cheapest. `ConversationSummaryMemory` re-summarises the entire history every turn, so cost and latency climb with conversation length while the stored output stays the same size [5]. Summarise N turns of history once per turn and the tokens you have paid to summarise by turn N scale with the square of N, even though what you keep does not grow at all [2]. Long sessions are where that bill arrives.
The two managed approaches also disagree about what a correction leaves behind. Mem0's decision set includes DELETE [7]; Zep's Graphiti never deletes, it invalidates, which the author frames as an audit trail you get for free and as overkill if you only ever need current state [11][13]. Same user correction, two different records afterwards: one store can show what it believed last month, the other cannot [3]. That is a retention question dressed as a library choice.
Two caveats on the source. It frames four architectures as claiming the same territory while solving almost none of the same problems, Letta included [14], but the text supplied here stops mid-sentence in the Zep section and never reaches Letta [18]. And it carries no benchmark figures at all [19], so the reconciliation quality that the whole argument turns on is described rather than measured. The mechanisms are checkable from the descriptions. The claim that one of them remembers better is not, yet.
