{"id":1452,"date":"2026-11-10T16:09:06","date_gmt":"2026-11-10T09:09:06","guid":{"rendered":"https:\/\/wordpress.nevatal.id\/2026\/11\/10\/decalove-architecture-performance-benchmark\/"},"modified":"2026-11-10T16:37:12","modified_gmt":"2026-11-10T09:37:12","slug":"decalove-architecture-performance-benchmark","status":"publish","type":"post","link":"https:\/\/wordpress.nevatal.id\/2026\/11\/10\/decalove-architecture-performance-benchmark\/","title":{"rendered":"Decalove – AI-Directed Visual Novel Game: Architecture & Performance Benchmark"},"content":{"rendered":"

Decalove – AI-Directed Visual Novel Game: Architecture & Performance Benchmark<\/h1>\n
\nKey Takeaways:<\/strong> Decalove merges Ren’Py client with a FastAPI backend to deliver an AI-directed visual novel where the AI Director generates dynamic narrative beats, tracks character relationships, and adapts in real-time. Players can choose authored options or type natural language prose, creating a seamless, emergent storytelling experience.\n<\/div>\n
\nLive Project Access:<\/strong> Internal Deployment<\/a>\n<\/div>\n

The Engineering Challenge: Why Decalove – AI-Directed Visual Novel Game Was Architected<\/h2>\n

Traditional visual novels rely on fixed branching trees, limiting emergent storytelling. Decalove solves this by introducing an AI Agent Story Engine that dynamically generates narrative beats ahead of the player’s progress, eliminating seams in the story. The challenge was to blend the deterministic nature of visual novel pacing with the fluidity of AI-driven content while maintaining real-time responsiveness and preserving authored world integrity.<\/p>\n

Core Architecture & Technical Stack Deep-Dive<\/h2>\n

Ren’Py Client<\/h3>\n

Decalove uses Ren’Py as the pure Python client for rendering UI, dialogues, and character sprites. This decoupled approach ensures platform independence and rapid asset iteration. The client communicates via asynchronous HTTP calls to the FastAPI backend, keeping UI responsiveness high.<\/p>\n

FastAPI Backend<\/h3>\n

The story engine resides in a FastAPI service, designed for high concurrency and low latency. It handles AI prompt generation, semantic memory retrieval, and director state management. The backend is containerized with Docker, enabling consistent deployments across development and production environments.<\/p>\n

AI Stack<\/h3>\n

OpenRouter LLM provides the core generative model for narrative beats. Vector Semantic Memory stores character relationships, emotional states, and past events, enabling contextually relevant story generation. Image Generation modules integrate with the backend to produce dynamic visuals when needed.<\/p>\n

Data Layers<\/h3>\n