Create interactive AI characters in Unity using local or remote LLMs.
Integrate large language models and RAG systems directly into Unity for conversational characters.
LLMUnity is a C# integration package for the Unity engine that brings large language models directly into your game projects. It is designed for Unity developers and game creators who want to add interactive AI characters with zero external internet dependencies.
The toolkit uses LlamaLib and llama.cpp under the hood to run LLM inference locally across PC, mobile, and VR platforms supporting CPU and GPU acceleration. It includes an advanced Retrieval-Augmented Generation (RAG) system for semantic search across your project's custom data.
It suits indie developers and game studios building single-player or local AI-driven experiences across multiple platforms. It does not suit teams looking for pre-hosted cloud AI APIs without handling local hardware performance.
Runs locally on PC, mobile, and VR without requiring internet access.
Delivers fast inference across CPU and GPUs including Nvidia, AMD, and Apple Metal.
Includes approximate nearest neighbor search to feed custom data into character knowledge.
Provides simple chat methods and callbacks for real-time token streaming.
Free to use for both personal and commercial purposes under its license. The only cost is running it yourself on client hardware.
880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
No, it runs entirely locally on the user's hardware without needing internet access.
It is tested and supported on PC, mobile, and VR across multiple Unity versions including LTS releases and Unity 6.
See Zekai first in Google