I built Opendria to explore how generative AI can be coupled with cognitive and psychological state machines to create immersive educational experiences.
Instead of using simple LLM wrappers, Opendria runs a backend simulation of brain, emotional, and cognitive states for 80 historical figures (like Einstein, Aristotle, Da Vinci, and Newton):
Cognitive Profiling: The backend dynamically calculates cognitive metrics (e.g., prefrontal cortex and temporal lobe scores) based on prompt sentiment and context.
Emotional & Somatic Simulation: It tracks variables like allostatic load, trust, and visceral tension. If a character has high stress or low trust, their vocabulary, patience, and character reactions shift organically.
Conversational Memory: Uses structured persistence layers to track learned concepts and memories across sessions, avoiding LLM "amnesia."
I’ve set up a free tier for testing the conversation flows. I’d love to get the community’s advice and feedback on:
The Simulation Engine: How does the transition of emotional and cognitive states feel in the dialogue?
UI/UX & Mobile: How is the mobile chat responsiveness?
Character Depth: What other parameters or historical figures should be integrated into the engine?
You can check out the app here: https://www.opendria.com – Let me know your thoughts!