chrxh/alien

ALIEN is a CUDA-powered artificial life simulation program.

What it solves

ALIEN provides a high-performance, GPU-accelerated environment for studying artificial life, emergent ecosystems, and evolutionary biology. It allows users to simulate complex, self-organizing digital organisms without needing to manually define fitness functions, enabling the study of how complexity and novelty arise in evolving systems.

How it works

The simulator uses a particle-based engine to model soft bodies, fluids, and rigid structures. Each organism is composed of cells with specialized functions (sensors, muscles, etc.) controlled by individual neural networks. These creatures interact, compete for energy, and reproduce based on their genomes. The simulation runs entirely on the GPU (CUDA/HIP), allowing for real-time interaction and the simulation of millions of particles. It also includes an MCP (Model Context Protocol) server, allowing AI agents to control the simulation, design genomes, or run experiments via natural language prompts.

Who it’s for

It is designed for artificial life researchers, generative artists, and hobbyists interested in complex systems, evolutionary biology, and digital simulation.

Highlights

  • GPU-Accelerated Physics: Simulates millions of particles in real-time with support for soft bodies, fluids, and hardware ray tracing.
  • Autonomous Evolution: Creatures evolve naturally through mutations in their neural networks and genomes, driven by environmental competition rather than pre-defined fitness functions.
  • AI Agent Integration: Built-in support for the Model Context Protocol (MCP) allows AI agents to interact with, build, and analyze the simulation.
  • Comprehensive Tooling: Includes a built-in genome editor, real-time statistics dashboard, and a community-driven simulation browser.

Related

  • Project
    taracodlabs/aiden

    An autonomous AI work engine that plans, executes, and verifies multi-step tasks across files, terminals, browsers, and APIs to produce proven results.

  • Project
    Kiln-AI/Kiln

    Kiln is an open‑source, local‑first workbench (desktop app + Python library) that lets teams build, evaluate, optimize, and ship LLM‑based products. It covers eval creation, prompt auto‑optimization, RAG pipelines, multi‑agent hierarchies, synthetic data generation, and zero‑code fine‑tuning across 190+ models, with Git‑based collaboration and offline support.

  • Project
    NVIDIA/aerial-cuda-accelerated-ran

    NVIDIA Aerial™ CUDA‑Accelerated RAN is an open‑source SDK that implements 5G PHY and MAC processing on NVIDIA GPUs. It includes CUDA kernels for channel coding, modulation, MIMO, and scheduling, plus a Python API for AI/ML research, all packaged in ready‑to‑run Docker containers.

  • Project
    Genesis-Embodied-AI/genesis-world

    A simulation platform for physical AI and robotics that combines a multi-physics engine, photo-realistic rendering, and a cross-platform compiler for scalable research.

  • Project
    haosulab/SAPIEN

    A physics-rich simulation environment for robotic vision and interaction, featuring a large-scale dataset of articulated objects for part-level understanding.