"We have got 95%+ benchmark on longMemEval by using a memory layer on long-running agents."
Hey Everyone, we created a memory infrastructure for long-running agents, and it beats mem0 and other big tools on LongMemEval benchmarks. If you are working on long-running agents, I would love to get feedback or suggestions over DM
Website: https://t.co/22RtFC8GnX
Github: https://t.co/KpyB1hNICm
@codyplof Have you thought about building an automated pipeline tool for this instead of using the chat? It could handle everything from AI idea generation to full deployment and testing
@Nate_Google_ This is interesting, how are you tracking and segmenting AI traffic accurately?
Especially since a lot of ChatGPT/AI traffic doesn’t pass clean referral data