Tarikh Keluaran Dirancang: Akan diumumkan

Tentang Permainan Ini

Explore beautiful but dangerous biomes in a world maintained by autonomous machines long after humanity vanished. Scavenge resources, restore forgotten systems, avoid or fight hostile machines, and descend into underground facilities as you search for the creators who abandoned you.

You are a special robot, maybe even the smartest, but not the strongest machine in this world. And you don’t need to be.

Every encounter is a choice: fight, evade, or outsmart. Not everything is your enemy, unless you make it so.

In a lonely world, B.O.B. is your closest companion, a luminous presence shifting form as it guides you and uncovers hidden paths.

A world that continues without you

The world is not empty.

Worker robots, drones, guards, mysterious Conductors, and Biome 2nd Admins carry out their roles in a system that continues all around you, independent of your presence.

Everything still serves a purpose, even if no one remembers why.

As you explore, you take control of eight abandoned robots, each with their own origin, biome, and purpose. Their paths gradually align, leading toward the G.O.D. Facility in search of their creators.

The story isn’t told directly. It’s uncovered through exploration, fragments, and encounters.

Prepare before you engage

Scraps and salvage are scattered across the world — or torn from other machines. Use them to modify weapons, craft armor, and adapt your build to what lies ahead.

The difference between making it through — or not — often comes down to how well prepared you are.

Resources matter. Positioning matters. Timing matters.

Uncover what remains

• Why were you abandoned?

• What happened to those who built this world of machines?

• Why are there beating hearts deep in the tunnels?

• What awaits inside the G.O.D. Facility?

Key Features

• Reactive world where enemies respond to your actions

• Multiple approaches to every encounter: fight, evade, or outsmart

• Scavenge and craft weapons, armor, and cosmetics

• Eight playable robots with distinct playstyles and perspectives

• Environmental storytelling uncovered through exploration

• A living ecosystem maintained by autonomous machines

Pendedahan Kandungan Dihasilkan AI

Pembangun menerangkan cara permainan mereka menggunakan Kandungan Dihasilkan AI seperti berikut:

We use AI to let our robots express themselves!
If a robot became alive, it wouldn’t come pre-programmed with the perfect way to express its thoughts or emotions — it would have to figure it out along the way. That’s why the hero robots in Endless Machines use AI to give voice to their thoughts and feelings.

What they say isn’t always polished or logical. It's quirky, weird, funny, and sometimes unexpectedly touching. It’s not a scripted, perfect dialogue. It’s more like a robot trying to make sense of the world — and itself — in real time.

This approach makes their personalities dynamic and unpredictable. For us, that’s what makes AI-driven dialogue a perfect fit for the game: It’s about learning, exploring, and growing — just like the robots themselves.

Under the hood, the game runs a small language model that has been custom fine-tuned for each robot's personality. It is instructed to speak through prompt engineering, ensuring the robot stays in character and relates to the game's lore. The model does not require online access.

We chose to use SmolLM because we were looking for a language model where the training background, technical setup, and use of data are transparent (open source and based on publicly available texts), and where the model can be run locally. We use this locally hosted language model (LLM) to generate text content during gameplay.

What the robots say in the game is defined and moderated by us. We have written a set of foundational texts that form the basis for each robot’s personality, tone, and way of expressing itself. From that foundation, they “build” further and develop over time. Endless Machines does not and cannot collect any data from the person playing the game.

All outputs are guided by custom prompt engineering, custom fine-tuning, and are controlled by local code at runtime to ensure appropriate content. More details on the model architecture and dataset can be found here:
🔗 https://huggingface.co/datasets/HuggingFaceTB/smoltalk