Keep key memory close
Pinned entries stay prominent, so the decisions and preferences you reference most are always a step away.
Recall
Pins and archive controls
Promote what matters, retire what doesn't — without losing a thing.
Overview
What Pins and archive controls does
Not every captured conversation deserves equal weight. Pinning lifts the memories you return to most — a core decision, a standing preference, a hard-won fix — so they stay prominent and easy to reach. Archiving does the opposite, moving stale or one-off entries out of the way so day-to-day recall stays focused on what is still relevant to current work.
Crucially, archiving is not deletion. The underlying conversation stays in the vault, keeping your source history complete and auditable; you are only adjusting what surfaces first. This lets you curate recall quality over time — sharpening what search and agents see — while preserving the full record in case an old thread becomes relevant again. Forgetting remains available separately when you actually want an entry hidden.
PinsArchive
Why it matters
The payoff for your AI memory
Reduce noise without loss
Archiving moves stale memory out of everyday recall while leaving the original conversation intact in the vault.
Curate recall over time
Steadily tuning pins and archives keeps what search and agents surface aligned with your current work.
How it works
From first launch to reusable memory
- 1
Open the Entries view or an individual entry.
- 2
Pin the memories you rely on most to keep them prominent.
- 3
Archive stale or one-off entries to clear them from everyday recall.
- 4
Restore or re-pin any entry later, since nothing is deleted.
FAQ
Common questions
Does archiving a memory delete it?
No. Archiving only removes an entry from everyday recall. The original conversation stays in the vault, so your source history remains complete and you can bring it back anytime.
What is the difference between archiving and forgetting?
Archiving de-emphasizes a memory while keeping it searchable. Forgetting hides an entry from search, MCP, imports, and injection until you remember it again.
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.