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.
Start Free
$300 Free Credits to Build on Google Cloud
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.
Argorha Pathfinding is an algorithm which permit you to find your way into a polygon soup ( 3D world ) efficently by precalculating a system of sectors and portals. AStar included. Demo in Download section, code on SVN.
This project is inspired by "lletters". It aims at displaying images and words corrosponding to alphabets but it integrates a "Text-To-Speech" (TTS) system to say out the words. The word list and corresponding images will be loaded from a XML file.
A C++ library for machine learning within dynamic systems. It provides methods such as the Kalman, unscented Kalman, and particle filters and smoothers, as well as useful classes such as common probability distributions and stochastic processes.
Plugin for Windows XP that put an Icon in Windows Bar and allow read the copied text(By mean Ctrl+C) using Festival a Speech To Text Synthesis Software.
An implementation of memory-prediction framework applied for image recognition. Based on Jeff Hawkins' book On Intelligence. It models the high-level hierarchical architecture of human neocortex and uses Bayesian belief revision for making predictions
Develop a neural network-based extension of Hebb/Hopfield networks to obtain powerful associative memory engine, capable of storing complex structured data, subject to its internal organization.
Provide capability of patterns "blending".
LabLOVE (Life On a Virtual Environment) is an evolutionary multi-agent simulation environment. It is fast, modular and extensible. Contains the reference implementation for the gridbrain algorithm.
Structlab is a machine learning C++ framework for structured domains, which provides a toolbox of learning methods and tools for preprocessing and visualization. It also provides a GUI to setup elaborate experiments in a visual and intuitive way.
Zigorat is a base code for creating multi-agent intelligent systems fitting in robocup soccer simulator 3d, done and created by Zigorat AI Research Team.
Animants are virtual ants. Their name comes from the combination of "ants" and "animats", an animat being "a sofware approximation of a living creature".
Animants aim to simulate the behaviour of living animals.
RegMAS (Regional Multi Agent Simulator) is a spatially explicit multi-agent model framework, developed in C++ language and designed for long-term simulations of effects of government policies over agricultural systems (farm sizes, incomes, land use..).
Subverse Project is a system to agent interaction in a virtual world with objective of studies and learns of ArtificialIntelligence algorithms. It is a set of parts to create a simulated environment of Artificial Inteligence and learning.
A suite of machine learning benchmarks where each agent must solve a lot of different tasks without recompilation. This means that the programmers cannot manually specify topologies or adjust parameters to specific tasks.
Computer chess engine written using Qt4, which works under Knights, Jose, Arena and other chess board GUI games. Uses bitboard game representation and alpha beta brute-force search to analyse chess positions.
Intelligent Assistant Constructor is software system based on Expert Systems. The main purpose is creating, teaching and asking Intelligent Assistants.