Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-09-04 · source-backed
LOCOMO-CONV rebuilds LoCoMo with four query styles (dialog, implicit, counterfactual, composed) and evaluates five memory systems on retrieval recall and end-to-end response quality. Implicit and composed queries expose big retrieval gaps that multi-facet query rewriting narrows for raw-turn memory but not abstractive memory. Strong retrieval also doesn't translate to response quality, and implicit queries show "silent grounding" where memory improves the answer without ever surfacing the gold fact. If you're benchmarking an agent memory layer on QA accuracy, you're measuring the easy half. arXiv 2609.03467
Each link below shares sources, entities, or timing with this story.
arXiv 2608.11879 benchmarked Mem0, Hindsight and Mastra Observational Memory across conversations up to 400 turns and 665 LoCoMo questions. Cost models built on conversation length miss badly because internal memory behavior dominates. Break-even against just replaying the ful...
Memori turns agent execution traces into structured persistent state, outperforming Zep, LangMem, and Mem0 on the LoCoMo benchmark while reducing prompt size by 67% vs Zep. Python and TypeScript SDKs. If you're building agents that need memory, benchmark this against whatever...
arXiv 2607.27090 targets the hidden tax in Mem0, MemGPT, and Zep: retrieved memory facts get re-prefilled on every single request. It precomputes each fact's KV representation, stores it on-GPU with a semantic embedding, and injects it into vLLM's paged cache via the KV-connec...
MemPalace (57,821 stars, v3.6.0) reports 96.6% raw recall@5 on LongMemEval with no LLM required, 98.4% with hybrid v4 on a held-out 450 questions, LoCoMo R@10 rising 60.3% → 88.9%, ConvoMem 92.9%, MemBench 80.3%, while explicitly refusing head-to-head comparison against Mem0,...
July 17, Product Hunt's #1 product was Unabyss for Claude: shared memory across all apps and LLMs, 598 votes. July 18, #1 was ZooData: "the data layer for AI agents," 606 votes. Neither is an application. Both are substrate. (Product Hunt) One launch is noise. Two consecutive...
Three-phase lifecycle: Phase 1 converts dialogue into MemCells (episodic traces + atomic facts + foresight signals); Phase 2 organizes into MemScenes with conflict resolution; Phase 3 performs MemScene-guided retrieval for minimal sufficient context. State-of-the-art on LoCoMo...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.