Day one: brilliant. They absorb everything — your project context, your preferences, your past decisions, your naming conventions. They ask exactly the right questions. They remember the answers. Day two: you ask them to build on what you discussed yesterday. They look at you blankly. Then they ask the same questions again. Same ones. Word for word. Except it’s worse than that. Because this assistant doesn’t just forget — they misremember. They confidently recall things that never happened, blend old decisions with new ones, treat contradictions as equally valid, and surface three-week-old context they should have discarded alongside the important context you actually need. This is what every AI agent you’re using right now is doing to your data. Not because the models are bad. Because the memory layer underneath them is architecturally broken. In March 2026, researchers at Cambridge and an independent AI lab published a paper that proved exactly why — and what the correct fix looks like. We built that fix… The paper opens with a clean diagnosis of the two dominant memory paradigms for AI: Paradigm 1: RAG (Retrieval-Augmented Generation) The paper’s core proposition: Apply the same principles to AI memory. Gate at write time. Archive rather than overwrite. The Experiment That Changes Everything Ungated RAG — store everything, filter at read time Then they scaled the distractors: Distractor ratio test (noise:signal in the memory store) The additional finding: write gating matches Self-RAG accuracy at one-ninth the query-time cost. Filtering once at write time is nine times cheaper than filtering on every read. The Salience Gate Composite Salience Score Supersession Chains Standard RAG performs overwrites. When something changes — a decision gets revised, a fact becomes stale, a user preference updates — the old value is either kept (creating contradiction) or deleted (destroying history). The paper proposes supersession chains instead: Standard RAG update: Part 2 — Why This Matters for Real Agent Work Every long-running agent session produces noise. Contradictory drafts. Interim decisions that got reversed. Redundant observations. Throwaway context that shouldn’t persist. In a flat, ungated store, all of this accumulates with equal weight — and at real session lengths, the 8:1 distractor ratio the paper tested isn’t a stress test. It’s Tuesday. Write on Medium Failure 1: Contradiction accumulation Part 3 — How VEKTOR Implements the Architecture the Paper Describes AUDN: Write-Time Gating Incoming: "User now prefers Railway over Vercel" AUDN Decision Paper equivalent MAGMA: The Graph That Supersession Chains Live In MAGMA — 4 Layer Associative Graph The memory.delta() Method // What changed on this topic in the last 30 days? REM: The Nightly Consolidation That Keeps the Gate Clean VEKTOR’s 7-phase REM consolidation cycle runs while idle: Raw session nodes (before REM) After REM: 50:1 compression Part 4 — The Memory Gaps You’re Actually Living With Gap 1: Your agent re-asks questions you’ve already answered. This is contradiction accumulation. The agent has equal-weight evidence for multiple positions and hedges by asking again. AUDN’s write-time gate prevents this — each update resolves the contradiction rather than adding to it. Gap 2: Your agent forgets why a decision was made. Three weeks ago you chose Postgres over MongoDB for specific reasons — EU data residency, your team’s expertise, a specific query pattern. Next month the agent suggests MongoDB. It doesn’t remember the reasoning, only the decision — and decisions without reasoning can always be re-litigated. VEKTOR’s causal layer stores the edge: chose Postgres → because: EU data residency + team expertise. Graph traversal surfaces the reasoning alongside the decision. The agent can apply that logic to new situations. Gap 3: Your agent treats stale context as current. Production credentials from six months ago. A naming convention that was revised. An API endpoint that changed. In a flat ungated store, these persist with the same weight as your most recent session’s context. VEKTOR’s temporal decay scoring and REM consolidation progressively deprioritise nodes that haven’t been reinforced — the old credentials don’t disappear, but they don’t compete with current context either. Gap 4: History is permanently unrecoverable. Standard RAG overwrites. Once the new state is stored, the prior state is gone. You can’t ask “what did we decide before we changed this?” because there’s no supersession chain — just the current value, no lineage. VEKTOR’s temporal layer preserves every superseded node. memory.delta() makes the full history queryable. The agent can answer both the current-state question and the history question from the same graph. The Architecture the Research Points To Current AI memory (ungated): Your agent has been working from a broken memory system. The fix isn’t a prompt. It isn’t a bigger context window. It’s a write-time gate, a graph with supersession chains, and a consolidation cycle that runs while you sleep. Get VEKTOR Slipstream → VEKTOR Slipstream is a local-first MCP server for persistent AI memory. AUDN write-time curation. MAGMA 4-layer graph. REM consolidation. 8ms recall. One-time purchase. Zero cloud. Ai Agentic Ai Memory Agentic Workflow Agentic Rag