Awesome AI Agents › Generative Agents Simulation
Gigax is a project that provides a runtime environment for NPCs (Non-Player Characters) powered by large language models (LLMs) that run locally on your hardware. The core idea is to enable NPCs in games or simulations to perform complex actions such as speaking, jumping, attacking, and any other user-defined behaviors, all driven by AI models fine-tuned specifically for this purpose. The project emphasizes fast inference times, achieving under one second on most GPUs, making it suitable for real-time applications. Gigax offers a variety of fine-tuned models available on the Huggingface hub, including versions based on Llama-3, Phi-3, and Mistral architectures. These models are also provided in GGUF format for CPU usage with llama_cpp, allowing flexibility in deployment depending on hardware capabilities. The system uses structured generation with the Outlines framework to ensure that the output format is always respected, which is critical for predictable NPC behavior. The project includes a Python API that allows developers to instantiate models, create NPCs, locations, items, and events, and then step through NPC actions with a simple asynchronous call. This makes it easy to integrate into game engines or other interactive environments. Gigax also plans to introduce a local server mode with a language-agnostic API and features like runtime quest generation and memory management with vector databases, which will further enhance NPC capabilities. Overall, Gigax aims to bring advanced AI-driven NPCs to games and simulations, providing developers with tools to create more immersive and dynamic interactive experiences. The project is actively maintained with ongoing feature development and community engagement through Discord and Twitter.
https://github.com/GigaxGames/gigax
This project provides a simulation framework for generative agents that mimic believable human behaviors within an interactive game environment, enabling running, saving, replaying, and demonstrating agent-based simulations.
Voyager is an open-ended embodied agent powered by large language models that autonomously explores and learns diverse skills in Minecraft through lifelong learning and an evolving skill library.
SFighterAI is a deep reinforcement learning-based AI agent designed to master and beat the final boss in Street Fighter II: Special Champion Edition using only game screen pixel data.
A comprehensive Godot framework for creating smooth and complex AI motion using steering behaviors in both 2D and 3D games.
WorldX turns a single sentence into a running simulated world, generating maps and characters with LLMs and letting autonomous agents act, remember and form stories inside it.
Control room for LLM agent societies: pause and scrub a running simulation, question individual residents, inject instructions into the next step, and export replayable experiment packs.
PyGame Learning Environment (PLE) is a Python-based reinforcement learning platform that provides a variety of games and tools to facilitate the development and testing of reinforcement learning algorithms.
A locally runnable, low-cost implementation of generative agents simulating human-like behavior in an interactive Dungeons & Dragons setting using large language models.