AI Characters that remember.

Build NPCs that hold grudges, spread gossip, and build relationships across every player session. Backed by persistent world infrastructure that keeps every interaction, emotion, and trust level alive.

How the platform is organized

Persistent world primitives describe your world. The platform foundation runs and connects them. Products are built on both.

Products

Built on the primitives and the foundation

Persistent world primitives

The foundation of your world’s state

Identity and relationships

Who is in your world, who knows whom, and how they feel about each other.

  • Player and NPC identities
  • Per-player trust, patience, and mood
  • NPC-to-NPC trust

Persistent state

What each entity carries from one session to the next.

  • Per-character memory
  • Relationship state
  • Identity state

Information flow

How what one entity knows reaches another.

  • Sharing between characters
  • Sharing presets and trust thresholds

Canon

What is true in your world.

  • Per-NPC knowledge files
  • Scene context

Platform foundation

Runs the primitives and connects your game

Control plane

Projects, team access, and keys.

  • Projects
  • Team invites
  • API keys

Developer platform

How your game connects.

  • Unity, Unreal, Godot, and Web SDKs
  • REST and WebSocket APIs
  • Dashboard and Playground
  • Cloud or Local per project

Products on the platform

Built on the same identities, relationships, and state.

MistScale AI

AI Characters

Characters that read and write persistent entity state: they remember each player, change with each relationship, and pass on what they learn.

  • Per-player memory
  • Mood and emotion
  • Trait drift
  • Grounding
  • Scene context
  • Voice
  • Arc on device
  • Bring your own model
Build your first character

Local inference

Run characters on the player's device.

A project can generate replies in the cloud or locally, inside your game. For local projects, MistScale still builds each prompt from the character, its knowledge, and its relationship with the player. The model on the device writes the reply.

Our model

Arc

A language model fine-tuned for in-world characters, running on the player's device.

Type
Fine-tuned LLM
Runs on
The player's device
Engine
Unity

Ready to run

Arc is tuned on the way MistScale describes a character: traits, mood, trust, and what it knows. The Unity SDK downloads it for you.

Bring your own model

Ship your own GGUF in one of five families: Qwen 3, Llama 3, Mistral, Gemma 4, or Phi-4. MistScale builds the prompt in that family's format. The model and its licence stay yours.

Cloud or Local, per project

Pick where replies are generated when you create a project, and change it later from the project overview. Every character in a project runs the same way.

Local inference is in the Unity SDK today; the Web, Godot, and Unreal SDKs run cloud projects. Local replies have no grounding check and no voice, and the Playground works with cloud projects only.

You decide who gossips.
And who they trust.

Word spreads between your characters, but only along the lines you draw. Set each one to Never, Cautious or Open, and set how much they trust each other.

Event

A player burns the village mill.

Give your world a memory.

Start free with AI Characters. Everything you build sits on the same persistent foundation.