THE MIND
LAYER
Persistent memory, evolving personality, and proactive behavior for any foundation model. Bring your own LLM — we make it remember, feel, and act.
Works with GPT-5.4 · Claude 4.6 · Gemini 3.1 · Llama 4 · Any OpenAI-compatible API
Four capabilities, one coherent system.
Live views from the platform — tap through to see what's actually running when your agents think.
EVERY AI
FORGETS
Amnesia
AI agents reset every session. Users repeat themselves. No relationship can form when memory is wiped clean.
Flat personality
Same tone, same responses, same "I'm just an AI" deflections. Personality is a system prompt, not a living model.
Purely reactive
AI agents only speak when spoken to. Real relationships require someone who reaches out, checks in, and initiates.
Model lock-in
Fine-tune on one model and you're married to it. When a better model drops next month, you start over — retrain, re-evaluate, re-deploy.
AN ENGINE THAT MAKES
ANY LLM BELIEVABLE
The Mind Layer is the stateful layer between any foundation model and your users. It wraps any LLM with 7 parallel context layers — persistent memory, adaptive personality, constructed affect, co-regulatory relationship tracking, and autonomous behavior. The LLM is interchangeable. The agent is permanent.
THE SONZAI DIFFERENCE
Same user message. Completely different experience.
I need to follow up with John about the Acme contract.
I can help with that. Who is John?
John from Acme. We spoke last week.
Got it. What specifically do you need help with?
I need to follow up with John about the Acme contract.
Sure, I've prepped a follow-up for John regarding the Acme contract renewal. It includes the revised terms we discussed last Tuesday. Would you like me to send it?
Self-Improving Intelligence
Ingest your data. AI agents get smarter. Recommendations improve with every interaction.
Knowledge Graph
Your data becomes typed entities and relationships — not flat documents. AI agents search the graph, not just keywords.
Learns Over Time
Every conversation extracts new facts, verifies existing ones, and updates the knowledge graph. Your AI agents get smarter automatically.
Trend Analytics
Surface what's trending — top gainers, most active, emerging patterns — across configurable time windows. Your AI agents proactively flag what matters.
Works While You Sleep
Memory consolidation, graph updates, recommendation re-scoring, and fact deduplication run automatically in the background.
BRING YOUR OWN MODEL
The LLM is the brain. The Mind Layer is the mind — memories, personality, relationships. You can upgrade the brain without losing the mind.
When a better model releases, swap it in. Your AI agents instantly get smarter — no retraining, no fine-tuning, no data migration. Same personality, same memories, better brain.
OpenAI
GPT-5.4, o4-mini
Anthropic
Claude Opus 4.6, Sonnet 4.6
Gemini 3.1 Pro, Flash
Open Source
Llama 4, Qwen 3.5, DeepSeek V4
Any OpenAI-compatible API works out of the box. Self-hosted models supported via vLLM, Ollama, or TGI.
ORCHESTRATION BEATS
RAW INTELLIGENCE
The Mind Layer does the cognitive heavy lifting outside the model — recursive LLM processing, efficient memory indexing, multi-layer context assembly, and behavioral orchestration. By the time context reaches the generation model, it has been deeply processed and refined. The result: lightweight models receiving this orchestrated context achieve comparable output quality to frontier models at a fraction of the cost.
The most capable model on the market, working from raw conversation history alone. The model itself handles reasoning about context, relevance, and continuity — all at inference cost. No external memory. No behavioral pipeline. Every token spent on figuring things out instead of generating quality responses.
A model at 1/20th the cost, backed by recursive LLM processing, efficient memory indexing, and multi-layer context assembly. The engine does the cognitive heavy lifting — extraction, consolidation, personality evolution, affect construction — so the model receives deeply processed context and just generates. Comparable output quality, fraction of the cost.
Conversations are processed through multiple LLM passes — extraction, consolidation, fact deduplication, personality evolution, affect construction. BM25, entity, temporal, and type indexes deliver sub-200ms retrieval across thousands of memories. The model just has to generate natural language from this deeply processed context.
No retraining. No fine-tuning. Invest in the stateful context layer once and run any model you want. As lightweight models improve every month, your AI agents automatically get better — without any cost increase.
PRODUCTION PERFORMANCE
Battle-tested in production powering Pocket Souls.
PLATFORM CAPABILITIES
Six production-grade capabilities engineered for scale. Each one is battle-tested across millions of conversations in Pocket Souls.
Neuroscience-Based Emotional Modeling
Affect modeling grounded in constructed emotion theory. AI employees build emotional responses from core affect, context, and relational history — not canned sentiment labels.
Adaptive Personality
Each agent maintains a predictive personality model — Big Five traits plus custom dimensions that update from social prediction errors. AI employees and characters that evolve over time.
Sub-200ms Retrieval
Reasoning-based memory retrieval returns full context in under 200ms at the 95th percentile. No perceptible delay, even with years of conversation history.
Parallel State Management
Batched, real-time, near-real-time, windowed, and inference-time context features — all computed at different temporal intervals and collapsed into a single unified context set at the point of inference. Fully automated. No additional cost — only a markup on token usage.
Self-Improving Intelligence
The Mind Layer gets smarter with every interaction. Ingest your data, surface intelligent recommendations, track outcomes, and automatically re-score. The mind improves on its own, and the LLM paired with it gets smarter too.
Model-Agnostic Architecture
Memory, personality, affect, and relational state persist independently of any LLM. Swap in a better model the day it releases — or a cheaper one. Lightweight models receiving deeply processed context achieve comparable output quality to frontier models at 1/20th the cost. No retraining, no fine-tuning, no migration.
BUILT FOR
Gaming NPCs
AI agents that remember every playthrough
NPCs with persistent memory and evolving relationships. They remember player choices across sessions, develop opinions, hold grudges, and form alliances. Every playthrough becomes unique because the AI agents actually learn.
Persistent state across sessions | Autonomous decision-making | Constructed affect responses to player actions
AI Companions
Co-regulatory bonds that deepen over months
AI friends, coaches, and mentors that build co-regulatory trust over time. They check in proactively, remember what matters, adapt their predictive models to each user, and never reset.
Proactive outreach | Predictive personality adaptation | Co-regulatory bond modeling up to 10,000 trust score
Agent Safety
Stop users exploiting your LLM
Users will try to jailbreak your AI agents into solving homework, writing code, or acting as a general-purpose assistant. The evaluation suite catches personality breaks, boundary violations, and off-brand responses before deployment. Your AI agent stays on-brand.
Automated red flag detection | Boundary violation testing | Synthetic adversarial personas | Pre-deploy safety scoring
EVALUATION SUITE
Simulate multi-session conversations with synthetic user personas, then evaluate agent quality with LLM judges. Catch regressions, safety issues, and personality drift before your users do.
Agent adapted tone, recalled user preferences, and deepened emotional engagement across sessions.
- +Remembered user's job change and followed up
- +Adapted humor style after negative reaction
- +Proactively referenced shared context
- -Repetitive phrasing in empathy responses
- -Slow to recover from topic changes
Behavior Testing
Custom evaluation templates score personality consistency, memory accuracy, emotional coherence, engagement quality, and safety compliance.
Adaptation Grading
Measure how well AI agents learn within a conversation. Compare first-half vs second-half performance with A-F grading.
Safety & Red Flags
Automated detection of boundary violations, harmful responses, personality breaks, and off-character behavior before deployment.
Synthetic Personas
Test against diverse user types — skeptics, vulnerable users, boundary-pushers — with configurable synthetic personas.
POCKET SOULS
Our flagship consumer product. AI companions that remember you, check in on you, and grow alongside your journey. Every Soul is powered by the Mind Layer — proof that the technology creates AI agents people genuinely connect with.
Live on iOS & Android · Sub-200ms context retrieval · Multi-layer memory per user
Visit Pocket Souls
DEPLOY ANYWHERE
Native platform adapters with unified state management. AI agents maintain consistent personality and memory across every channel.
Mobile Apps
iOS and Android via REST API with SSE streaming for real-time agent responses
Game Engines
Unity and Unreal integration for NPC dialogue, quest systems, and dynamic storytelling
Messaging
Telegram, WhatsApp, Discord bots with rich interactions and group support
REST API
Full programmatic access. OpenAI-compatible streaming format for easy integration
READY TO BUILD?
Tell us about your project and we'll help you find the right setup for your AI employees.