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.
VentureBeat

Mem0's scalable memory promises more reliable AI agents that remembers context across lengthy conversations

Researchers at Mem0 have introduced two new memory architectures designed to enable Large Language Models (LLMs) to maintain coherent and consistent conversations over extended periods. Their ...
dbta

Memgraph’s Atomic GraphRAG Speeds Up the Use of Graph-Based RAG Across Multiple Data Sources

Memgraph, a leader in open-source, in-memory graph databases, is introducing a new capability designed to accelerate business adoption of graph-based retrieval-augmented generation (GraphRAG), Atomic ...
dbta

Memgraph Creates Toolkit for Non-Graph Users to Jumpstart the Journey to Full GraphRAG AI Capability

Memgraph, a leader in open-source in-memory graph databases purpose-built for dynamic, real-time enterprise applications, is releasing two new tools specifically architected to open up the power of ...