Awesome AI Agents › Generative Agents Simulation
Interactive LLM Powered NPCs is an innovative open-source project designed to revolutionize player interactions with non-player characters (NPCs) in video games. It enables players to engage in natural, voice-based conversations with NPCs across various popular open-world games such as Cyberpunk 2077, Assassin's Creed, and GTA 5 without requiring any modifications to the game's source code. The system leverages advanced technologies including speech-to-text conversion, facial recognition to identify NPCs, and large language models (LLMs) to generate contextually relevant and personality-driven responses. It also uses vector stores to provide NPCs with extensive memory capacity, allowing for more immersive and continuous dialogue experiences. The project integrates sadtalker technology to synchronize NPC lip movements with generated speech, enhancing realism by animating facial expressions based on the NPC's dialogue. Additionally, it incorporates emotion recognition through the player's webcam, enabling NPCs to respond dynamically to the player's facial expressions, thus deepening the interaction. The system supports pre-conversation files that contain iconic lines and dialogue styles for each character, ensuring that NPC responses remain authentic and true to their personalities. One of the standout features is its ability to facilitate conversations even during non-visual interactions, such as horseback riding or combat, by allowing players to initiate dialogue by naming the NPC followed by their speech. This ensures uninterrupted and seamless communication throughout gameplay. The installation process involves setting up Python, Git, and other dependencies, with detailed instructions provided for ease of use. Overall, Interactive LLM Powered NPCs significantly enhances the gaming experience by bringing NPCs to life with realistic, meaningful, and context-aware conversations, transforming static game worlds into dynamic and engaging environments.
https://github.com/AkshitIreddy/Interactive-LLM-Powered-NPCs
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.