mem0
@mem0ai
Memory Layer for your AI agents. Open source:
28 Following 18.8K Followers
We evaluated Nemotron-3-Embed from @NVIDIAAI for our @mem0ai memory retrieval pipeline
Tested on longmemeval: retrieval@10 improved from 78.71 to 80.38 over qwen-3-600m
A few things made it a good fit for how we operate: open weights, NVFP4 support on Blackwell for efficient inference, and strong throughput, which matters for a system where writes happen constantly.
A breakdown on how Mem0 uses embeddings and Nemotron-3-embed evaluation below👇
Show more
Earlier this month, we hosted a mem0rable game night: Mario Kart tournament at the Mem0 office with SF community leaders & growth teams!
Vibes all night!
At mem0, we love creating more memories!
Show more
