Esment Blog
Memory for AI assistants that actually remember.
Essays, deep dives and field notes from the Esment team — on persistent memory, local-first AI, and building agents that start from what you know.
Latest
The case for memory that your assistant cannot lose
Every assistant starts every conversation from zero. A persistent memory store changes what "starting" means — and why it has to be inspectable, local, and deterministic.
All posts
Local-first is a feature, not a constraint
Running memory on your own machine is not a limitation we accepted — it is the design that makes the product honest. Here is the architecture that makes it fast, private and portable.
What we learned building a temporal knowledge graph
A memory that cannot forget is a liability. The hard part of a knowledge graph for assistant memory is not storage — it is deciding what survives, what merges, and what dies.
Follow along
New posts when there is something worth reading.
Field notes on memory, local-first AI and the engine behind Esment — a few times a quarter, never more.