Gamer
Official Implementation of Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agents
- 686
- Apache-2.0
- 4 d ago
Official Implementation of Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agents
A Survey on Large Language Model-Based Game Agents (ACM CSUR)
Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds. Weights on Hugging Face.
A local PTCG practice and rules-simulation project built with Godot 4.6 and GDScript.
A lightweight, script-driven game engine your AI can drive — download the SDK, then let your AI build the game.
[ICML 2026] GameVerse: Can Vision-Language Models Learn from Video-based Reflection?
🕵 Code for our EMNLP 2025 Main paper: "FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games"
LLM-powered AI agent framework for 4X mobile strategy games (Rise of Kingdoms, Evony, Lords Mobile, etc.). 5-layer hybrid architecture: OCR → FSM → World Model → Workflows → LLM Vision. 99% cheaper than pure LLM approach.
XOShift AI agent built with Python using minimax, alpha-beta pruning, iterative deepening, and heuristic board evaluation.
GAT — Godot Agent Team: a full-cycle (design→implementation) Godot game-development agent / 游戏制作智能体. Multi-agent, style-locked asset generation, self-evolving knowledge base; runs under both Claude Code and Codex.
Deterministic, resource-first Arena Hero agent with hierarchical threat response, safe unattended deployment, and optional offline AI review
A local vision game agent for Apple Silicon. Screenshot perception, Laya/Core ML decisions, Qwen/MLX planning, camera control, loot clicks, and evidence-based review.
AI agent that plays Fishing Frenzy autonomously via Claude Code. Install, play, compete.