NKAI-Decision-Team/LLM-PySC2

LLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmind's PySC2 Learning Environment API as a Python LLM Environment.

41
/ 100
Emerging

This project allows researchers to test how large language models (LLMs) can play StarCraft II. It takes StarCraft II game observations, converts them into text or images, and lets LLMs make decisions and execute actions within the game. Researchers studying AI agents and decision-making in complex environments would use this tool.

152 stars. No commits in the last 6 months.

Use this if you are a researcher developing and evaluating large language models (LLMs) for complex strategy game environments like StarCraft II, especially for multi-agent scenarios.

Not ideal if you are looking for a pre-built StarCraft II AI for general gameplay or competitive matches, as this is a research environment for LLM development.

AI research LLM evaluation game AI multi-agent systems StarCraft II
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

152

Forks

14

Language

Python

License

Apache-2.0

Last pushed

Apr 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/NKAI-Decision-Team/LLM-PySC2"

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