VoiceMem splits agent memory into factual and affective halves and retrieves in 134 ms.

The top-upvoted paper on Hugging Face Daily Papers this week at 167 upvotes runs a parallel "left brain" for factual memory and "right brain" for affective attribution and dual-node persona modeling, with streaming memory I/O and interchangeable backends. At top-5 retrieval the left brain beats Mem0 at top-200 by nearly 30 points, the right brain sets state of the art on three persona benchmarks with a 4.29-point aggregate gain, and retrieval completes inside standard VAD latency so it adds no conversational delay. (arXiv 2608.26005)