New agentic memory framework uses 118K tokens per query. LangMem burns through 3.26M.

NUS researchers' MRAgent framework reduces LLM agent memory retrieval to 118K tokens per query — vs. 3.26M for LangMem — using step-by-step reasoning.

Microsoft unveils Memora to tackle AI agents’ memory problem

The research project promises more efficient long-term recall by organizing knowledge around abstractions and cue-based ...
Decrypt

Perplexity's AI Agent Now Has a Brain That Learns From Its Own Mistakes

Perplexity's Brain is a self-improving memory layer that tracks what the AI agent Computer did, what worked, and what failed.
Forbes

Google’s TurboQuant Compression Could Increase Demand For AI Memory

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. On March 24, 2026 Amir Zandieh and Vahab Mirrokni from Google Research published an article ...
Forbes

SOCAMM2 Is The Memory Standard AI Is Looking For

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. AI infrastructure cannot evolve at the speed of model innovation. Processor design cycles ...
The Register-Guard

Evermind AI Launches EverMemOS to Transform Artificial Intelligence Through Foundational Memory Infrastructure

Modern artificial intelligence systems operate with a fundamental paradox: they demonstrate remarkable reasoning capabilities while simultaneously suffering from systematic amnesia. Large language ...
VentureBeat

Oracle converges the AI data stack to give enterprise agents a single version of truth

Enterprise data teams moving agentic AI into production are hitting a consistent failure point at the data tier. Agents built across a vector store, a relational database, a graph store and a ...