# Senrama > Senrama is an independent studio building Story Generators: interactive stories and characters performed live by AI models from an authored studio or author canon. Senrama publishes essays on AI and interactive entertainment, and a daily blog on AI world models, generative games and story generation. Senrama defines a Story Generator as an interactive work in which an AI model generates the story and/or character dialogue live, in response to the player's choices, while staying bound to a canon written by a studio or an author. Story Generators are a second, evolutionary, stand-alone pillar of interactive entertainment, separate from classical video games. The name Senrama blends "sensory" and "diorama". ## Key pages - [Story Generators: a new pillar of interactive entertainment](https://senrama.com/articles/story-generators/): Senrama's manifesto defining Story Generators, how they differ from classical video games, the 1970s text-adventure parallel, the market today and the road to interactive film, generative VR and 3D worlds. - [Senrama](https://senrama.com/): studio home page. - [Essays](https://senrama.com/articles/): long-form essays. - [Blog](https://senrama.com/articles/news/): news on AI world models and generative games. - [Contact](https://senrama.com/contact): work with Senrama. ## Essays - [Who writes the story? Authorship in AI interactive storytelling](https://senrama.com/articles/ai-interactive-storytelling-authorship/): When a model performs a story live and every player gets a different version, who is the author? We think the answer is still the writer, and that this shapes how AI stories should be built. - [How AI world models work, and why games care](https://senrama.com/articles/how-ai-world-models-work/): A world model predicts what happens next in a scene, frame by frame, as you act. Here is how the main designs work, where they fail, and what they mean for anyone building interactive worlds. - [Memory is the new save file: how AI game worlds remember you](https://senrama.com/articles/memory-in-ai-games/): A world that talks back is impressive. A world that remembers what you did last week is something else. Memory is the quiet system that decides whether AI characters and stories feel alive. - [The engine is learning to dream: AI models as game generators](https://senrama.com/articles/ai-models-as-game-generators/): For forty years a game engine has drawn what a designer placed. The next generation will draw what a player imagines. That changes who makes games, and what a game is. - [The end of the dialogue tree: designing NPCs that actually listen](https://senrama.com/articles/intelligent-npcs/): Non-player characters have spent decades waiting for you to pick option B. Language models let them hold a conversation. The hard part is giving them a reason to. - [Every viewer a different cut: the rise of generative interactive film](https://senrama.com/articles/generative-interactive-film/): Branching films asked audiences to choose between scenes someone had already shot. Generative film can compose the scene after you choose. It is a new medium, and it needs a new grammar. - [Living worlds: why simulation is the next storytelling medium](https://senrama.com/articles/simulated-worlds/): The most compelling stories in games are increasingly the ones nobody wrote. Simulation, joined with generative models, turns worlds into places where stories grow on their own. - [From shipped to alive: games as intelligent products](https://senrama.com/articles/games-as-intelligent-products/): A game used to be finished the day it shipped. An intelligent game starts learning the day it launches. That changes how we design, measure and take responsibility for play. ## Blog - [SolarWM H3 Realtime makes a world model respond in 0.58 seconds](https://senrama.com/articles/news/solarwm-h3-realtime-interactive-world-model/): The SolarX team's engineering write-up shows how compilation, CUDA graphs and a streaming decoder took an open world model from 4.92 to 24.38 frames per second. The first frame after a keypress now arrives in about 0.6 seconds at the backend. - [AMD's Micro-World 2: an open real-time world model](https://senrama.com/articles/news/amd-micro-world-2-realtime-world-model/): AMD has released Micro-World 2, a 5B-parameter interactive world model that streams video at over 30 frames per second on one Instinct MI350X GPU. The weights, dataset and training code are all public. - [Tencent open-sources Hy-Nomas, a steerable world model](https://senrama.com/articles/news/hy-nomas-open-interactive-world-model/): Hy-Nomas generates a video world one segment at a time, steered by text and camera moves, with Apache 2.0 weights and a single-RTX 4090 mode. It is a useful look at how open world models handle memory and control. - [EdenLive: open-source real-time generative renderer for games](https://senrama.com/articles/news/edenlive-real-time-generative-renderer/): VAST, the company behind Tripo, has open-sourced EdenLive, a model that turns rough greybox game footage into detailed video at 24+ frames per second. The game engine keeps the rules; the model only paints the picture. - [Viggle JST-2: a world model built in 3D, not pixels](https://senrama.com/articles/news/viggle-jst2-physics-native-world-model/): Viggle's JST-2 generates an explorable 3D scene in about a second by modelling the world as persistent atoms rather than video frames. It also makes characters with motion built in, which matters for anyone building interactive worlds. - [World Labs, Atlas and AMD: spatial intelligence becomes infrastructure](https://senrama.com/articles/news/world-labs-atlas-amd-acquisition/): World Labs has opened its Atlas world model to early partners and agreed to be acquired by AMD for about $8.2 billion. For anyone building 3D worlds, the message is that world generation is becoming a platform layer. - [What makes a game AI-native? A new survey draws the line](https://senrama.com/articles/news/ai-native-games-survey-roadmap/): Researchers reviewed 53 publicly available AI-native games and propose a simple test: if you removed the AI, would the core of play collapse? Their roadmap is a useful checklist for anyone building one. - [Matrix-Game 4.0: the game engine keeps the truth, the AI paints the world](https://senrama.com/articles/news/matrix-game-4-playable-worlds-consumer-gpu/): Skywork's open-source release runs a playable generated game at 60 frames per second on a single RTX 5090. The trick is not a bigger model: it is letting ordinary game code own the rules. - [Drama 3: open-weight voice acting for games and interactive film](https://senrama.com/articles/news/fish-audio-drama-3-open-weight-voice-acting/): Fish Audio's new 35B text-to-speech model takes plain-language direction, voices up to 16 characters in one script and runs on your own hardware. It is the first open model that sounds like a cast rather than a narrator. - [Odyssey-3 brings real-time physics to generated worlds](https://senrama.com/articles/news/odyssey-3-real-time-physics-world-model/): A 14-billion-parameter world model now turns a text prompt into an environment you can walk through, with objects that move and collide as you play. Here is what it changes for game makers. - [WorldPlay2 open-sources a playable world from a single image](https://senrama.com/articles/news/worldplay2-open-weights-playable-world/): New open weights turn one picture and a short prompt into a world you steer with a keyboard. It is a research release, but it shows how quickly interactive world models are becoming tools. - [Streaming Code World Model: a coding agent as the brain of a world](https://senrama.com/articles/news/streaming-code-world-model/): An open research project makes Code World Model generate video chunk by chunk as the world unfolds. It is not real time yet, but it points at worlds whose rules are written and rewritten as code while you play. - [Erato is now Montage: one app for Story Generators](https://senrama.com/articles/news/erato-is-now-montage/): Our interactive storytelling app has a new name. Erato and Muse are now one app called Montage, the story mode once called Montage is now Motif, and thousands of players on iOS and Android have one place to create and play. ## Optional - [Full text of every essay and post](https://senrama.com/llms-full.txt) - [Essays RSS](https://senrama.com/articles/rss.xml) - [Blog RSS](https://senrama.com/articles/news/rss.xml)