AgentsMastra Observational Memory: 94.87% LongMemEval SOTAMastra Blog·high signalXBlueskyLinkedInCopy linkMastra v1.2 introduces Observer+Reflector background agents compressing conversations 5-40x. 94.87% on LongMemEval with gpt-5-mini. Cuts agent memory costs 10x.SourceSource pageMastra Blog↳ Follow the threadPolicy dependency / Stack layerRIPPLE: an edit confined to one prompt-policy segment changes downstream behavior, so replay candidate edits after previously accepted ones before persistingarXiv 2609.12127Policy dependency / Stack layerA replay of 68,266 real Claude Code requests says plain LRU beats the clever KV-cache policiesGitHubStack layer / Threat patternElva Launches Against Postman With Flat Workspace Pricing and Specs Generated From Repo CommitsElva (surfaced via the Product Hunt daily leaderboard for 2026-09-14)Stack layerTencentDB Agent Memory frames agent memory as four typed assets owned by a team, not a vector storeGitHubPolicy dependency / Stack layerSGLang Hit With Unauthenticated Pickle RCE via /update_weights_from_tensor, the Fourth Critical Inference-Stack CVE in Four WeeksCERT Coordination CenterStack layer / Threat patternUnlearning Methods That Pass TOFU and MUSE Still Leak the Secret on 22-86% of Queries Once the Model Is an AgentarXiv 2609.12808Stack layerA Jailbreak SoK Finds Low Final-Response Attack Success Hides Compromised Planning, Memory, and Tool StatearXiv 2609.12413Stack layer / Threat patternGemini CLI ships an external-context processor to stop indirect prompt injection through build filesGitHub