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.
Try It Free
Enterprise-grade ITSM, for every business
Give your IT, operations, and business teams the ability to deliver exceptional services—without the complexity.
Freshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
Python Machine learning library with multi-core support. Wraps existing ML libraries in order to be able to run and analyse experiments with one front-end API. Currently supports MLP, GA, GP, ESN and RBF algorithms.
The CVR-Lib (Computer Vision and Robotics Library) is a C++ object oriented library for computer vision. It provides lots of functionality to solve mathematical problems, many image processing and analysis algorithms, classification tools, and much more.
A system for playing chess with a computer player using a real chess board. An experiment in learning the techniques of Computer Vision and having fun in the process.
Deploy in 115+ regions with the modern database for every enterprise.
MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
Active Shape/Appearance Model Library (ASMLibrary/AAMLibrary) source code, which includes ASMBuilding/AAMBuilding as well as ASMFitting/AAMFitting algorithm. It is developped under OpenCV 1.0 for locating features in a face and face recognition.
Snackware is a project aimed to create a "competition of coders" by making different classes or functions to battle amongst themselves against the rules of a game. It's not a traditional game, anyway, since it work with no human intervention.
Artifical Life simulator that employs techniques from evolutionary computing to design embodied neural networks. Essentially, simple organisms run around in a small 3-D world and compete and breed with one another. Please visit the Wiki for orientation.
The XCS library aims at providing an opensource framework to study and develop applications related to learning classifier systems.
In particular, it is focused on the learning classifier system models introduced by Stewart Wilson in [1,2].
<p>
[1
The package implements a variety of tools for categorization of multivariate data such as boosted decision trees, bagging and random forest, bump hunting (PRIM), a multi-class learner and others.
This is implementation of parallel genetic algorithm with "ring" insular topology. Algorithm provides a dynamic choice of genetic operators in the evolution of. The library supports the 26 genetic operators. This is cross-platform GA written in С++.
Applications contributed for URBI (Universal RealTime Behoavior Interface). URBI is a scripted command language used to control robots (AIBO pioneer..) as well as a robot-independant execution and developpement plateform. www.urbiforge.com www.gostai.com
The Rossum Project is an attempt to collect and distribute robotics software. We are seeking help with our first project, a mobile-robot simulator featuring a 2-D virtual world, and new work including artificial intelligence and robot-control logic.
A common task in indoor robotics is line-following. This code detects and tracks arbitrarily shaped curves in digital images at a rate of 15 Hz on images of size 600x320, which makes it usable for real-time tasks. It is written in C++ and tested on linux
Library for Recurrent Neural Networks supporting local and global learning rules and structure modification. For processing of the RNN, a computational efficient representation can be chosen.
This project consists of neurodynamic simulation software, for large scale associative memories and self-organizing competetive nets. NVIDIA's CUDA library is used for acceleration. Written in C++ and meant for a Unix-like environment.
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.