alvion427/PerroPastor

Run Llama based LLMs in Unity entirely in compute shaders with no dependencies

32
/ 100
Emerging

This tool helps game developers integrate small language models (LLMs) directly into their Unity games. You feed in a Llama-based LLM model, and it runs entirely on the game's GPU, producing text responses within the game itself. This is for game developers who want to add real-time, low-latency AI interactions without needing external servers.

106 stars. No commits in the last 6 months.

Use this if you are a game developer building a Unity game and want to embed Llama-based LLMs for in-game AI, like character dialogue or interactive storytelling, without relying on external cloud services.

Not ideal if you are developing non-Unity applications, require very large LLMs, or need to run models on CPUs rather than GPUs.

game-development in-game-AI Unity-engine real-time-AI offline-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

106

Forks

5

Language

C#

License

MIT

Last pushed

Feb 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/alvion427/PerroPastor"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.