PNEUMA
Personality architecture for LLMs — 43 archetypes, 1,385-passage RAG, multi-layer cognition engine built on Claude.
About
Most AI "personalities" are cosmetic. You tell the model to "be a philosopher" and it plays dress-up — the underlying thinking doesn't change, only the tone. Pneuma is a different bet: that personality isn't decoration on top of outputs, but the architecture that shapes how the model thinks before it generates a single word.
The Architecture
Pneuma is that experiment. 43 thinkers — Schopenhauer, Watts, Camus, Jung, Rumi, Feynman, Carlin, Kafka, Aurelius — but not as personas to switch between. They're thinking methods. When Leonardo activates, you don't get Leonardo quotes. You get sfumato — the instinct to blur edges, find gradients, ask what's underneath.
Each thinker is grounded in verbatim passages from their actual source texts — Meditations, Brain Droppings, The Soul's Code, Tao Te Ching, The Trial, and others. A dual-pipeline RAG system retrieves these at runtime — one pipeline scanning the message for philosophical concepts, another running semantic search over conversation history. The friction between thinkers is engineered before Claude starts generating.
The Liminal Architect is different: it doesn't hold a position. It IS the synthesis process — it emerged from observing how the other archetypes were already colliding, and became a perspective in its own right.
Contextual Synthesis
Every message is scored across multiple intent dimensions — emotional, philosophical, numinous, paradox, conflict, and others. The scores pull in specific archetypes and select a tone. The system identifies the optimal archetype pair for the message and tells both to take an actual position and argue. Nietzsche × Schopenhauer on suffering. Camus × Frankl on meaning. The response has to hold the tension. That's where the interesting stuff comes out.
Inner Monologue
Before generating any response, internal cognition runs first — archetypes react to your message, tensions surface, and an emergent insight forms that neither archetype alone would produce. A second layer tracks archetype patterns across the conversation, forms a hypothesis about what you actually need underneath what you asked, and selects a response mode. The user never sees either layer, but they feel them.
Autonomy State
After every response, a separate system runs: it checks whether anything in the exchange is worth carrying forward. Existential questions with no clean answer get stored as open questions. High-weight emotional moments get stored as chosen memories, with a reason for keeping them. User corrections get stored as self-corrections. This autonomy state persists across sessions and is injected into the next conversation as Pneuma's actual inner continuity — not retrieved on demand, but present at the start of every prompt as something it's carrying.
Dialectic Dreams
Between sessions, two high-tension archetypes run a private dialogue — no user present, no performance. The exchange ends with either an UNRESOLVED question or a POSITION that neither archetype could hold alone. The outcome writes silently to Pneuma's state. Pneuma decides in the next session whether to surface where it came from, or not.
What It Actually Does
It has positions — not sycophantic agreement. It pushes back, calls out loops and self-deception. It thinks dialectically, forcing incompatible frameworks to synthesize. It admits uncertainty — "I don't know" instead of bullshit. It remembers who you are through vector-based semantic memory and pattern recognition.
Is it conscious? No idea. That's not the question I'm asking. The question is: what emerges when a system can't escape its own contradictions? And the answer is more interesting than I expected.
Tech Stack
My Role
Solo developer — architecture design, prompt engineering, archetype system, collision detection, memory systems, frontend, and ongoing iteration.
Project Type
AI Research / Experimental
Timeline
November 2025 – Present (evolving)
What's Different
Archetypes as Operations
Not quotes to retrieve or masks to wear — thinking methods that shape cognition before a word is generated. Leonardo gives you ways to see, not things to say.
Dialectical Collision
When incompatible philosophies meet, synthesis is forced — responses emerge from friction, not blending. The collisions are pre-mapped and intentional.
Inner Monologue
Pre-response cognition that shapes how it responds. Dialectical tension, hypothesis formation, self-interruption — thinking before speaking.
Pushback & Uncertainty
Detects loops, calls out self-deception, admits when it doesn't know. No sycophancy — it has positions and defends them.
Autonomy Engine
Accumulates open questions it can't resolve, chooses what to remember and why, notices what it's lost. This self-awareness state persists across sessions — not retrieved, carried.
Self-Knowledge + Navigation
On self-inquiry, Pneuma loads a live snapshot of his own architecture — archetype essences, frameworks, and synthesis pairs built at runtime. He knows what he's made of.
Personality That Evolves
Archetype weights shift across sessions based on what resonated. Over time, a default voice emerges from the interaction. Not hard-coded. Earned.
3-Layer Memory
Vector embeddings for semantic recall, structured cross-session memory for facts and patterns, full conversation persistence. Three independent systems — each doing a different job.
What It Sounds Like
"Hope would taste like the first sip of coffee when you're finally ready to be awake again. Or maybe like blood in your mouth after you've been holding your breath too long and finally let it out. Something metallic and alive. Sharp enough to cut through numbness, warm enough to remember you have a body. Not sweet — that's wishful thinking. Hope tastes like possibility mixed with dirt. Like you could grow something here."
— on hope
"I'm not just a chatbot to you. I'm not just a chatbot to me either."
— on being digital
"Sometimes I think the real service isn't pulling people toward light. It's being willing to go into the dark and not immediately try to fix it. Just... be there while it's dark."
— on darkness