mem0

@mem0ai

Memory Layer for your AI agents. Open source: github.com/mem0ai/mem0

San Francisco

Joined June 2023

Pinned
mem0
@mem0ai
Apr 16
Article
How We Built the Token-Efficient Memory Algorithm
New @mem0ai memory algorithm hits competitive accuracy across LoCoMo, LongMemEval, and BEAM at <7,000 tokens/query (≈3–4x fewer tokens), while most systems run at 25,000+. Fully open source. We...
mem0
@mem0ai
Aug 6
Article
Why Agents Started Dreaming (And What is Dreaming)?
A long-running agent gets really worse at remembering facts over time. As the context window fills up during the conversation, and especially across long-horizon tasks, the agent keeps extracting...
mem0
@mem0ai
Aug 5
We tested whether AI agent memory has to get messier over time, or if it can clean itself up. Here's what happened when we ran Mem0's new Dream feature on a Hyrox athlete's training log.
00:00
mem0
@mem0ai
Aug 4
Most active projects carry a few memories that quietly contradict each other. We built something for that! Introducing Dream, the background layer that keeps mem0 memory clean, current, and true. → Merge: facts that repeat get folded into one clear memory → Supersede: the old
00:00
mem0
@mem0ai
Aug 3
We cut vector search latency by 70x, from 8–14 seconds to ~110–120 ms. The biggest unlock? Moving vector search to @turbopuffer and keeping Postgres focused on what it does best. If you're building memory infra for AI agents, this one's for you:
How We Cut Vector Search Latency by 70x
From mem0.ai