mem0 (@mem0ai) / X

Pinned

Today we are releasing DolphinBench: Mapping the Pareto frontier of agent memory. Coding, tool use, and long-context retrieval already have strong public benchmarks. Memory still mostly gets graded as a quiz: ask a question, judge the answer, maybe report precision and recall.

Deshraj Yadav

@deshrajdry

Sep 22

Today we are releasing DolphinBench: Mapping the Pareto frontier of agent memory. Coding, tool use, and long-context retrieval already have strong public benchmarks. Memory still mostly gets graded as a quiz: ask a question, judge the answer, maybe report precision and recall.

How to choose the model that writes your memories

Every add request to Mem0 runs a language model. It reads the conversation and decides what to keep: a user’s preferences, a deadline, a change of plans. With bring your own key (BYOK), you can pick

X. It’s what’s happening

We're throwing a Halloween happy hour for our users and contributors 🎃 If you’re in SF on Oct 27, come on over, meet the team, and yap memory.. Costumes encouraged of course..

Every memory has two clocks: - when the event happened - when the system learned about it A deep dive into eight temporal scenarios in consumer apps, and how to handle each one:

Article

Managing Time in AI Memory

Consumer agents run for months and years with the same user. A companion, a coach, a journaling app: each one collects thousands of small facts over that time, and most of those facts are only true

Jev-Mem: Memory Decisions Without an LLM

Jev-Mem shows that memory decisions don't need an LLM that writes sentences. Its thresholds were tested with one model on one benchmark. Every agent memory system makes a ton of small decisions, all

30