The BEAM benchmark, developed by the team behind Suprflo, evaluates AI agent memory over long, multi-session histories with changing facts, ranging from 100K to 10 million tokens. It measures distinct…
A developer discovered that the widely-cited LOCOMO benchmark for AI memory excludes 22.5% of its questions—those testing whether a system can correctly say 'I don't know'—and instructs models to neve…
Swafra, an open-source semantic memory system for AI assistants, achieved 94.7% recall_all@10 on the LongMemEval benchmark for long-term memory. The tool works as an MCP server with Claude Desktop, Cl…
Oracle Agent Memory, a database-native memory substrate built on Oracle Database, achieves 93.8% accuracy on LongMemEval while using about 10.7x fewer tokens than flat-history baselines, according to …
Researchers introduced NapMem, a framework that transforms long-term user memory into a structured action space for conversational agents, enabling active navigation across memory granularities. Train…
Researchers at arXiv identified a memory-update gap in LLM agents, where accuracy drops from 92% to 77% when using bounded memory instead of full context, even with frontier models like gpt-5.4. The g…
Mem0, an open-source memory layer for AI agents with nearly 60,000 GitHub stars, has released v3.0 with temporal reasoning and multi-tenant isolation. The project scored 94.8 on LongMemEval and 91.6 o…
Developer Shan Rizvi forked the open-source CozoDB into MnesticDB, adding cognitive primitives for AI agents. The new database reduces index build times from 89 seconds to 8 seconds and improves retri…
Writer's research paper reports that memory systems can amplify sycophancy by up to 25x, but the amplification is traced to two design decisions: an evaluation prompt ordering the model to answer sole…
Backboard has launched Backboard Development Studio, an open beta coding harness that uses a memory-first architecture to outperform frontier AI models while relying on open-source models. The system,…
Backboard has achieved the top position on both the LoCoMo and LongMemEval benchmarks for long-term AI memory, a feat no other system has matched without modifying the original evaluation guidelines. …
A developer is training a compact model called Operator to execute actions within the Kernel Memory Protocol (KMP), a contract for reading, navigating, and writing memory in the Underpass Kernel. The …
Researchers have developed the Deterministic Memory Framework (DMF), a CPU-first memory system for conversational AI agents that replaces generative large language model compression with a fully deter…
Researchers have introduced "Behavioral Specification" as a new interpretive layer for AI memory, arguing that current systems optimized for factual recall fail to capture how a specific person proces…
Zep announced Observations, a new context type that automatically discovers patterns and insights across Context Graphs, capturing behaviors, decisions, and preferences that emerge across multiple epi…
According to the "Is Grep All You Need?" study (arXiv:2605.15184), researchers wired both a literal grep tool and a vector-search tool into the same agents to run 116 LongMemEval questions, finding th…