Field notes and landscape pieces on AI memory — shorter reads for the big-picture curious.
9 articles
Mem0, Letta, Zep/Graphiti, Cognee, Supermemory compared: integration posture, self-host reality, temporal handling, and why benchmark scores need a harness.
Ontology vs schema vs topology: one shared commitment, five different contracts, and what missing data means — false, unknown, or forbidden.
OpenAI's Record & Replay for Codex and Anthropic's composable skills arrived the same week. Two stacks, one shift: encoding how work is done and making the procedure callable. The ownership question follows.
Cursor's valuation, Anthropic's dreaming preview, Google's Memory Bank: different architectures, same shift. Persistent memory has stopped being a research conversation and become a choice builders can no longer defer.
Orogat and Mansour name four failure modes of treating agent memory as storage, and propose GEM: four state-level operations instead of record-level CRUD. Why the abstraction, not the engine, is the problem.
AI agent memory fails three ways: statelessness, context rot, and lost-in-the-middle. Bigger context windows trade one failure for another and add token spend.
AI memory landscape 2026: how persistent memory became a production discipline — platform features, funded startups, the LoCoMo benchmark, and open problems.
When AI cites what does not exist: a case study of a recombination hallucination that passed four of five checks, and why persistent memory needs verification.
AI memory market 2025-2026: platform memory from OpenAI, Anthropic, Google, Microsoft, xAI, plus startups, funding rounds, and context-management trends.