New customers can spin up VMs, build with AI, and query data at no cost.
Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
Start Free
Build Agents and Models on One Platform
Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.
Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
NeurAnim is a research aid for computational neuroscience. It is used to visualise and animate neural network simulations in 3D, and to render movies of these animations for use in presentations.
This is my implementation of Langton's Ant (a popular turing machine, see http://en.wikipedia.org/wiki/Langton%27s_ant for more information) using C#. Supports multiple ants and threading. Video: http://www.youtube.com/watch?v=Vu9C_1DH31k
The sunflower library provides programming abstractions developed at the Autonomous Systems Lab http://www.asl.ethz.ch/. It contains a complete path planning and obstacle avoidance system, common mobile robotics tasks abstractions, and a 2D simulator.
Graphical interactive windows application and library written in .Net/C# for simulating and controlling robots. Including firmware for ATmega8 to be controlled by the C# library and circuits for the ATmega8 controller board and L298-based motor board
SPLITNEURON is a completely new approach to large-scale, biologically plausible, neural-network simulation library based on data structures and methods directly coded into database and conceived to explicitly share load on multiple machines.
A genetic algorithm in Python for evolving programs that write a given string to an allocated dataspace, using a made-up machine language with only 7 instructions and flow reversal.
A unified collection of algorithms for Artificial Life. It includes evolutionary algorithms, neural networks, data mining tools, compilers, among others.
This project is a complete cross-platform (Windows, Linux) framework for Evolutionary Computation in pure python. See the project site at http://pyevolve.sourceforge.net or the blog at http://pyevolve.sourceforge.net/wordpress
This project intends to create a bacteria simulator framework, with some realistic bacteria control methods based on chemical signaling, simple sensors, motors and neural networks. The bacteria will evolve in a genetic algorithm environment.
The Mars Rover Simulator project is based on the evolutionary robotics paradigm where an artificial agent acquires its skills through the process of artificial evolution. This simulator can be useful to evolve neural network controllers for the rover
Java based multi-agent platform built on an organizational model (agent, group, role). MadKit provides general agent facilities (lifecycle management, message passing, distribution, ...), and allows high heterogeneity in agents.
Headrand is a static library wrote in c that contains functions to simulate complex systems or make statistical analysis with a new approach called "random function computing"
MASyV (Multi-Agent System Visualization) enables one to write agent-based models/cellular automata, eg. in C, visualize them in real time & capture to movie file with MASyVs GUI & message passing lib. Includes examples: Hello World, ants, viral infection
A holistic evolutionary simulator with some support for neural networks, genetic inheritance, and spatial morphologies in simulated organisms. Dedicated to Carl Sagan.
Siafu simulates individual agents and their context, from home to city-wide scenarios. As a developer, you use the API to write your simulation for the purposes of data-set generation, test or visualization, optionally hooking it to your own application.
This project is dedicated to developing a simulation of the financial market using multi-agent approach. This kind of simulation is often called an Artificial Stock Market (ASM).
DCOPolis is a framework for comparing and deploying distributed decision processes in heterogeneous environments, including simulation in a virtual machine.
SimIS presents an agent-based simulation environment from multiagent research to simulate Internet-of-Services systems. The simulation environment bases on Repast Simphony 1.2 (http://repast.sourceforge.net/).