Flag memories for review when their supporting
Flag memories for review when their supporting evidence changes, not just because they are old
Recall
Evidence-Aware Memory
Know when a memory can no longer be trusted. 1AIVault flags memories for review when the evidence behind them changes — age alone never makes a memory stale — and keeps confirmed-stale context out of what your AI tools recall.
Overview
What Evidence-Aware Memory does
Know when a memory can no longer be trusted. 1AIVault flags memories for review when the evidence behind them changes — age alone never makes a memory stale — and keeps confirmed-stale context out of what your AI tools recall.
The danger with a growing memory vault is not old notes — it is confidently wrong ones. Evidence-Aware Memory watches the sources behind your memories and marks one for review the moment its evidence shifts, so you can verify it before an AI tool leans on it. Confirmed-stale memory stays out of recall entirely, and the freshness signal travels with your vault across every device.
Recallv1.12.0
Why it matters
The payoff for your AI memory
Compare a memory with the source that
Compare a memory with the source that changed and confirm, update, or mark it stale
Warn connected AI tools about memory that
Warn connected AI tools about memory that needs review before they rely on it
Keep confirmed-stale memory out of normal recall
Keep confirmed-stale memory out of normal recall so it can't steer an answer
How it works
From first launch to reusable memory
- 1
Open 1AIVault and go to the relevant workspace.
- 2
Use Evidence-Aware Memory as part of your capture, classify, recall, and connect workflow.
- 3
Reuse the resulting memory across your connected AI tools.
FAQ
Common questions
Does a memory go stale just because it is old?
No. Age alone never marks a memory stale. A memory is flagged for review only when the evidence it was built from actually changes — so long-lived, still-true notes keep working normally.
How do I review a flagged memory?
Open it to compare the memory with the source that changed, side by side. Check it again and confirm it is still correct, update it, or mark it stale.
Do my AI tools see freshness warnings?
Yes. Connected tools receive a warning for memory that needs review, and memory you confirm as stale is kept out of normal recall so it can't quietly influence an answer.
Does freshness follow my vault to other devices?
It does. Freshness status travels with portable exports and folder sync, so every device shares the same understanding of what can still be trusted.
Related
More Recall features
Dashboard & Activity
Dashboard view shows a vault summary plus a live activity feed of every read, write, and classification across all connected AI tools. Deep links via `aivault://` open the app from anywhere.
Learn moreLast Used Stripe on Every Memory
Every entry detail header shows 'Last used X ago by Source · Nx this week' so you know which AI tools are touching a memory and how often.
Learn moreSemantic Search
Local embeddings — via Xenova Transformers (ONNX), llama.cpp (GGUF), or a remote embedding API — so AI clients can recall memories by meaning, not just keywords.
Learn moreLocal memory, shared everywhere
Give every AI tool the same memory.
Start free, import real conversations, and reuse your memory across every AI agent you already use.