Fetching from the wire…
01
02
03
04
05
06
07
08
Skills2026-08-11 · source-backed
SodaMem extracts typed events with source attribution and tracks temporal validity so superseded facts are structurally retired rather than competing at retrieval time. 92.8% on LongMemEval-S at $0.00161 per question, median ~18.3k tokens on deepseek-v4-flash, code released. If your agent memory is an append-only log, this is a cheap upgrade path.
Each link below shares sources, entities, or timing with this story.
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...
Four parallel retrieval strategies (semantic, temporal, entity, opinion) merged through cross-encoder reranking with atomic fact extraction on every write. Ships an MCP server for Claude Code adoption via single JSON config. Source
Google launched agentic video understanding across Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite (Google). Instead of scanning a video start to finish at a fixed sample rate, the model runs an internal loop deciding what to watch, at what speed, and through which channel: fra...
The attack needs no instruction, trigger, or retriever optimization, just plainly worded false assertions generated in one pass against a LongMemEval corpus. A four-stage screening pipeline that reaches 0.832 recall on indirect prompt injection rejected none of the poisoned me...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.