How poqpoq World builds companions that reason, remember, and perceive — at scale, in real time.
For twenty years, virtual worlds have been experientially empty. Artists filled them with architecture and landscapes, but the characters do not think, the spaces do not respond, and the result feels more like wandering through a museum after hours than inhabiting a living world.
poqpoq World takes an AI-first approach. Rather than building a world and hoping people fill it, we built a platform where the world itself is alive with intelligence. Every companion reasons about your relationship, remembers your conversations, and perceives the space around them just as you do.
Creating a single intelligent companion is straightforward when you can throw unlimited compute at one conversation. The difficulty emerges at scale: hundreds of concurrent users, each with unique relationships, conversation histories, and spatial context.
Without careful engineering, a naive implementation demands massive infrastructure and still delivers sluggish responses. Our companions achieve sub-two-second response times, efficient memory retrieval, and intelligent spatial filtering — while maintaining rich, personalized relationships with every user.
The companion system is built on five principles that work together to make real-time, personalized AI possible at scale.
Conversations are encoded into 768-dimensional vectors that
capture meaning, not just words. When a
companion searches for relevant memories, it finds semantically similar
experiences. A question about "weather" retrieves memories about sunny
days, climate, and forecasts — concepts that keyword search would miss
entirely.
Not all memories carry equal weight. Each is automatically scored on a
0.0 to 1.0 scale based on emotional weight
and commitment language. A casual "hmm" scores
0.1; "I promise to help you" scores
0.9. Companions prioritize what truly
matters in your relationship.
Human attention is not constant — we focus intensely during important moments, then relax into background awareness. Companions mirror this with three attention levels: high urgency (5-second updates when you speak), active (12-second updates during interaction), and baseline (120-second updates when idle). This biological model reduces unnecessary computation by 70%.
Memory search combines two strategies: vector similarity at 70% weight finds semantically related memories through approximate nearest-neighbor search, while keyword matching at 30% weight ensures exact terms are never missed. The combination delivers both broad understanding and precise factual recall.
A capable language model with a carefully curated
~2,000-token context window outperforms a smaller model
drowning in massive, noisy input. Think of it this way: a master chef
creates a memorable meal from five perfect ingredients, while a novice
struggles even with a fully stocked pantry. Quality of context matters
more than quantity.
The companion system operates across three layers, rendered in real time by Babylon.js with WebGPU acceleration. Optimization happens at every stage — from the moment a character is typed to the final token streaming back to the screen.
This documentation is structured as a technical narrative. Each chapter builds on the previous ones.