Learn
Conceptual deep-dives into how the Relationship Layer thinks — memory shape, personality dynamics, and the self-improvement loop.
If the Docs explain what each feature does, Learn explains why it works the way it does — the model, the loop, and the trade-offs you can tune.
Deep dives
Architecture
How the platform, orchestrator, and your backend fit together — and where each piece of state lives.
How agents improve over time
The complete picture of automatic learning: memory decay, consolidation, dedup, retrieval policy, personality drift, breakthroughs, and shadow rollouts.
Agent insights
What the system reveals about an agent's inner state — and how to use it to debug, audit, or fine-tune behavior.
Proactive behavior
When agents reach out on their own — wakeups, schedules, and the policies that govern them.
Big Five personality
OCEAN dimensions, behavioral facets, and how personality shifts in response to interactions.
Mood model
Four mood dimensions, decay rates, and the events that move them.
Build something with it
Once the model is clear, the Tutorials in Guides walk you end-to-end through a concrete project.