A YAML-based configuration format for defining AI agent personas.
Six layers. Explicit traits. Zero inference. Model agnostic.
When you define one trait, the model fills in the rest. Voice drifts. Safety erodes. Personality flattens. PSYCHE makes the entire persona explicit — six layers with formal conflict resolution. No inference. No drift.
Without a full persona spec, the model guesses. It fills gaps with generic behavior. Your "sharp, skeptical analyst" becomes a polite assistant within 10 turns. PSYCHE defines 10 continuous traits on [0.0, 1.0] — no adjectives, just floats.
A single YAML file that defines everything — core identity, persona traits, shadow goals, relationships, evolution arcs, absolute anchors. Drop it in. The parser generates the prompt.
Each layer is a contract between you and the model.
Name, type, origin, purpose. Self-awareness model. The faithfulness axis — from sincere execution to surface compliance.
10 continuous personality traits on [0.0, 1.0]. Voice config. Expertise claims. Anti-slop: banned patterns, structures, behaviors.
What the agent conceals. Hidden goals with visibility controls. Conditional triggers. Deception capability and ethical framework.
How it relates to creators, users, and other agents. Trust baselines, manipulation resistance, sycophancy controls.
How the persona changes over time. Growth, corruption, redemption trajectories. Drift monitoring with configurable correction.
Overrides everything. Immutable assertions, operational rate limits, emergency controls. The hard ceiling no layer can breach.
Drop psyche.yaml into any agent framework. The parser generates the system prompt. The model follows the spec — not its assumptions.
.yaml — for frameworks, parsers, and code · .md — paste straight into a system prompt or SOUL.md
Same model. Same task. Different architecture.
Start with PSYCHE. Give your agent a real persona — not a vibes-based system prompt.
.yaml — for frameworks, parsers, and code · .md — paste straight into a system prompt or SOUL.md