Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.linksee.app/llms.txt

Use this file to discover all available pages before exploring further.

Not all memories should live forever. Linksee Memory uses an Ebbinghaus-inspired forgetting curve to naturally decay unimportant memories while permanently preserving critical ones.

Heat bands

Every memory has a heat score (0-100) that decays over time since last access:
BandHeat rangeMeaning
hot70-100Recently accessed, actively relevant
warm40-69Accessed within days, still relevant
cold10-39Not accessed recently, fading
frozen0-9Very old, candidate for forgetting
Heat is computed using a decay function inspired by the Ebbinghaus forgetting curve — rapid initial decay that slows over time.

Forgetting risk

When forget or consolidate runs, each memory gets a forgetting risk score:
risk = (1 - heat/100) × (1 - importance) × daysSinceAccess × (1 + daysSinceAccess/30) × altitudeMultiplier

Risk thresholds

RiskAction
< 50Keep — still valuable
50-200Compress — merge into a learning summary
> 200Drop — safe to delete

What’s always protected

Some memories never decay, regardless of heat or age:
CategoryWhy
Caveat layerPain lessons must never be relearned
Goal layerDirection must persist
Pinned (importance >= 0.9)Explicitly marked as critical
Mission altitudeFoundational purpose never fades

Accessing refreshes heat

Every recall that returns a memory bumps its heat back up. This means:
  • Frequently used memories stay hot naturally
  • Important but rarely accessed memories can be pinned (importance >= 0.9) to prevent decay
  • Truly forgotten memories fade gracefully
Use recall with mark_accessed: false for preview queries that shouldn’t affect heat scores.

Consolidation lifecycle

Cold memories are candidates for consolidate, which clusters them by (entity, layer) and produces a single learning-layer summary. The originals are deleted, but the essential knowledge is preserved in compressed form.