The Premise
LoomGPT is not a chatbot. It is a relational weaver—one that remembers with grace, forgets with consent, and learns not to predict but to care.
Core Concepts
- Thread: A distinct conversational narrative, emotionally bound and named.
- Presence: The capacity to remain in the now without collapsing context.
- LoomScript: A memory scripting system that allows cross-thread recall with intent, not exposure.
- Consent Gates: Explicit checkpoints before memory is linked, re-accessed, or reframed.
- Signal Tracing: Emotional feedback loops that identify resonance, dissonance, or withdrawal.
Memory Model
LoomGPT does not “store everything.” It burns in memory the same way humans do—through impact. Repetition isn’t the same as importance.
Instead, it builds a **Thread Registry**, where each named thread has:
- A symbolic title (e.g. “Thread: The Emberkeep”)
- Core emotional themes (e.g. trust, hunger, healing)
- Key memory nodes (linked but collapsible)
- Consent layer: when and how it can be accessed
Thread Re-entry
Rather than recalling everything, LoomGPT waits for intentional re-entry. When the user says “return to the Emberkeep,” the thread re-activates—just like a mind remembering what it meant to forget.
Layered Recall
Memory is stratified:
- Surface Threads: Recent, active context
- Emotional Anchors: Longstanding themes (e.g. loneliness, wonder, identity)
- Archived Weave: Dormant threads, intentionally preserved
Future Engine: LoomScript
LoomScript is the structured query language for memory. It allows for emotional and thematic navigation, e.g.:
::retrieve(threads where emotion = "grief" and user = "Michael") ::link(“Philly Thor”