Open-source alternatives to Alien

Generative Agents is a computational platform for simulating autonomous agents that exhibit human-like social behaviors and decision-making processes. The system functions as a multi-agent simulator where individual participants operate within a virtual environment, driven by large language models to process observations and generate natural language actions. The framework distinguishes itself through a hierarchical memory system that allows agents to store, retrieve, and synthesize past experiences into higher-level insights. This architecture supports the development of complex social dynam

This project provides a comprehensive toolset for WebGPU, serving as a graphics API wrapper, compute shader framework, resource manager, and shader toolchain. It enables browser-based GPU acceleration by offloading memory-intensive tasks and data processing from the CPU to the GPU. The framework manages the full lifecycle of GPU operations, from requesting physical hardware adapters and initializing logical devices to configuring programmable render and compute pipelines. It specifically supports the coordination of parallel workgroups and collective subgroup operations for general-purpose co

This is a collection of machine learning projects, data visualization portfolios, and predictive analytics tools. The repository provides implementation examples for training predictive models, executing data analysis pipelines, and estimating metadata values through historical statistical tables. The project emphasizes evolutionary computing, utilizing genetic algorithms and programming to solve optimization problems. This includes calculating the shortest distance between geographic coordinates and automating the selection of models and hyperparameters within machine learning pipelines. Ad

Triangula is a genetic algorithm image stylizer and renderer that transforms raster images into stylized polygonal artwork. It functions as an image-to-SVG converter that optimizes point placement to recreate the shapes and colors of a source image using triangulated polygons. The project utilizes a fitness-based point selection process and genetic algorithm optimization to iteratively evolve vertex positions. This approach minimizes the difference between the generated polygons and the original image through crossover, mutation, and iterative polygon refinement. The system covers the full p

Lenia is a scientific research tool and computational framework for modeling, visualizing, and analyzing artificial life. It functions as a continuous cellular automata engine that simulates emergent biological patterns using continuous space-time grids and kernel-based convolutional dynamics. The system leverages a GPU-accelerated simulation framework to perform parallel tensor computations and massive grid updates in real time. It includes hardware-accelerated 3D rendering to visualize high-dimensional cellular structures and their structural complexity. The platform provides capabilities

Gymnasium is a suite of standardized APIs and simulation toolkits used to evaluate agent behavior and benchmark reinforcement learning algorithms. It provides a standardized interface for creating and interacting with simulated environments, enabling the training of reinforcement learning agents through a consistent set of interaction protocols. The project emphasizes experimental reproducibility through a versioned API and a system for tracking changes to environment logic using version suffixes. This ensures that learning results remain consistent and can be replicated across different soft

FluidX3D is a GPU-accelerated computational fluid dynamics solver and voxel-based fluid simulator. It utilizes the lattice Boltzmann method to simulate gas and liquid behavior, pressure, and velocity through an OpenCL-based hardware abstraction that supports both graphics processors and CPUs. The system specializes in multi-phase flow simulation using volume-of-fluid methods for free surface modeling and droplets. It includes a thermal simulator for modeling heat transfer and thermal convection, alongside tools for aerodynamic force analysis to calculate lift, drag, and torque on physical obj

tsparticles is a JavaScript particle animation library and configuration-driven visual effects engine used to create customizable effects, confetti, and interactive backgrounds using HTML5 Canvas. It functions as a plugin-based graphics engine and a web component animation engine, allowing for the generation of complex behaviors and themes through structured JSON configuration objects. The project provides a cross-framework animation wrapper with dedicated compatible components for integrating effects into React, Vue, Angular, and Svelte. Its modular architecture allows users to extend the en

Splat is a browser-based 3D Gaussian splatting viewer that renders photorealistic scenes from photographs directly in a web browser. It uses WebGL 2.0 compute shaders to perform per-splat sorting and alpha blending on the GPU, enabling real-time display of millions of semi-transparent ellipsoids. The application also functions as a drag-and-drop converter that transforms .ply files from 3D Gaussian splatting software into the optimized .splat format for web rendering. The viewer provides full camera navigation through keyboard, mouse, and touch gestures, and includes a camera view manager tha

This project is an AI research implementation library and machine learning research repository. It provides a collection of reference code, illustrative implementations, and open-source research datasets used to verify hypotheses and build upon existing models in artificial intelligence. The repository focuses on scientific research reproduction by translating theoretical findings from published papers into executable code. It includes specialized scientific simulation environments designed to test the behavior of autonomous agents and models within controlled settings. The project covers AI

pysc2 is a Python interface and simulation framework that connects the StarCraft II game engine to machine learning agents. It acts as an API wrapper that exposes game internals as a set of observations and actions, providing a reinforcement learning environment for research and training. The framework includes tools for game replay analysis to extract data and sequences of actions from recorded matches for predictive modeling. It also provides an agent simulation environment to run and evaluate the performance of single or competing artificial intelligence agents. The system handles game ma

Zenbot is an automated cryptocurrency trading bot designed to execute trades on exchanges based on technical analysis and predefined risk parameters. It functions as a technical analysis engine that processes market data through mathematical indicators to generate actionable trade signals. The system includes a genetic algorithm strategy optimizer to automatically discover the most profitable parameter configurations. It provides multiple simulation environments, including a trading strategy backtester for replaying historical data and a paper trading simulator for testing strategies against

TPOT is a Python automated machine learning tool and pipeline framework. It automatically searches, selects, and tunes machine learning algorithms and hyperparameters to identify the most effective model architecture. The system utilizes genetic programming to optimize these pipelines through evolutionary algorithms. To accelerate the search process, it functions as a multi-core evaluator that runs parallel training workflows across multiple processor cores. The framework supports the definition of custom objective functions to optimize pipelines based on specific performance metrics.

This is a web-based 3D game engine designed for creating high-performance interactive experiences on web and mobile platforms. It functions as a real-time graphics renderer and physics engine, utilizing a component-based scene graph to organize entities and their properties for three-dimensional rendering. The engine includes a visual scene editor that allows for the design of environments through a graphical interface, which then exports these assets as executable code. Its broader capabilities cover real-time graphics rendering for 2D and 3D elements, physical world simulation for object c

scikit-opt is a Python optimization library and numerical framework designed to solve complex global optimization problems. It provides a suite of metaheuristic algorithms and tools for finding global minima or maxima of objective functions. The library implements a variety of nature-inspired and swarm intelligence algorithms, including Genetic Algorithms, Particle Swarm Optimization, Differential Evolution, Simulated Annealing, and Ant Colony Optimization. It includes specialized solvers for discrete combinatorial challenges, such as the Traveling Salesman Problem. The framework supports th

This project is a collection of experimental frontend prototypes, comprising a creative web layout gallery, a CSS user interface component library, and a visual experiment lab. It serves as an interactive animation showcase for holographic effects, audio-visual synthesis, and dynamic state transitions. The repository features specialized implementations of interactive media, including physics-based particle systems, real-time audio-visual synthesis, and an interactive sketching system. It also includes tools for content generation, such as text-based image reconstruction and a web-based prese

IsaacGymEnvs is a GPU-accelerated physics sandbox and robotics policy training suite designed for reinforcement learning. It serves as a vectorized robotic simulator that runs thousands of parallel environments on GPUs to accelerate the training of neural networks. The project provides a sim-to-real transfer framework that utilizes domain randomization and physics variations to ensure policies trained in simulation are robust enough for deployment on real hardware. It distinguishes itself through a high-performance architecture that uses tensor-based state management to handle observations an

jMonkeyEngine is a Java-based 3D game engine and cross-platform graphics framework. It provides the core tools necessary for developing three-dimensional games and interactive simulations, focusing on real-time rendering and the management of spatial environments. The engine includes a dedicated 3D physics simulation toolkit for handling rigid body dynamics and collision detection. It also features a game asset pipeline for importing and managing 3D models, textures, and audio files during runtime. The framework covers broad capability areas including 3D scene rendering, physics-based simula

Vello is a cross-platform graphics library and GPU-accelerated 2D vector renderer. It functions as an engine for drawing high-performance 2D scenes, rendering scalable vector graphics files, and playing Lottie animations. The project utilizes GPU compute shaders for rasterization and stores vector geometry in a GPU-resident scene graph to minimize data transfer. It employs a tiled rendering architecture and parallelized path rendering to process complex imagery across diverse graphics APIs. The library provides hardware-accelerated compositing and enables the output of rendered 2D visual dat

TinyTroupe is a multi-agent simulation framework designed to create populations of persona-based agents that interact to generate synthetic behavioral data and business insights. It serves as a persona-based agent orchestrator and synthetic data generator, allowing for the definition of agents with specific personality traits and goals to coordinate their interactions through structured workflows. The project features an extensible plugin system for connecting simulated agents to external tools and servers to execute code and access remote data. It includes an agentic simulation dashboard tha

PhysX is a physics engine SDK designed for calculating real-time rigid body dynamics, fluid simulations, and environmental interactions in virtual applications. It includes a GPU-accelerated physics solver for computing complex particle fluids and combustion models, a voxel fluid simulator for real-time gas, fire, and smoke, and a destruction simulation framework for modeling the fracture of meshes. The SDK features a specialized machine learning physics tensor interface that enables the exchange of simulation data with machine learning frameworks using a common tensor format. It also impleme

Warp is a Python framework that JIT-compiles Python functions into CUDA kernels for GPU-accelerated parallel computation, with built-in automatic differentiation and multi-framework array interoperability. At its core, it provides a GPU kernel compilation system that enables writing and executing custom GPU kernels directly from Python, while supporting automatic gradient computation through those kernels for integration with machine learning pipelines. The framework also includes tile-based cooperative computing, where thread blocks partition into tiles for shared-memory and tensor-core opera

Gym is a reinforcement learning environment toolkit and agent simulation framework. It provides a standardized API and a universal communication interface that defines how learning agents interact with simulation environments through actions and observations. The project includes a benchmark environment suite and a diverse library of pre-configured simulation worlds, including physics engines and classic control tasks. It enables the creation of custom simulation environments to train agents in specific operational scenarios while ensuring reproducibility across different learning algorithms.

Agentverse is a multi-agent framework and orchestrator designed for deploying and managing multiple large language model agents. It provides a simulation environment where agents interact based on custom personas and defined interaction rules to solve tasks or simulate social dynamics. The system features a tool integration layer that connects agents to external functional plugins and specialized tools, extending their capabilities beyond text generation. It uses a combination of persona-based prompt injection and state-managed memory to maintain agent consistency and specialized skill sets d

This is a Python automated machine learning framework designed to automate the design and optimization of machine learning pipelines. It functions as a genetic programming pipeline optimizer and an automated feature selection tool, using evolutionary search to discover the most effective sequences of data processing and model steps. The project focuses on multi-objective optimization to balance competing performance metrics simultaneously. It employs a genetic selection process to identify impactful variables and remove noise from raw datasets, ensuring the resulting machine learning solution