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
$300 Free Credits to Build on Google Cloud
New to Google Cloud? Get $300 in credits to explore Compute Engine, BigQuery, Cloud Run, Gemini Enterprise Agent Platform, and more.
Start your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
The Zeus-Framework is a C++ framework using the paradigm of Cell Computing Model for Linux and Windows. Implements biological behaviours (cloning, genetic algorithmes, ect.). Used for grid computing, distribute systems etc.
A feedback-enhanced framework for routing in wireless sensor networks. Speeds up the process of implementing routing techniques. Enables piggybacking of routing information on data packets. Written for the Omnet++ simulator and the Mobility Framework.
The Drools.NET is a .NET port for Drools, which is a java Rules Engine based on Charles Forgy's Rete algorithm. Drools.NET enables .NET developers/Users to exploit the powerful Rule Engine like Drools through a completely managed .NET code base.
CAIR is an e-learning project that allow users and subjects management. You can associate pupils and teachers to subjects and works for this subjects. There are special functionalities for those subjects related to Robocup development.
JPA is platform independent, hybrid agent framework that enables users to use natural language to access applications such as email, file system, web services, database, and internet; all through a single user interface.
Using agent technology JAMAS (Java Awareness Multi-Agent System) tries to assist distributed programmers in coordinating parallel development of Java code. E-JAMAS implements JAMAS and it’s features as a plug-in for the Eclipse platform.
General purpose agents using reinforcement learning. Combines radial basis functions, temporal difference learning, planning, uncertainty estimations, and curiosity. Intended to be an out-of-the-box solution for roboticists and game developers.
Lay a foundation for success with Tested Reference Architectures developed by Fortinet’s experts. Learn more in this white paper.
Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
D-Cog (Declarative-Cognition) is a Java based framework for training software components (reusable, object-oriented, interface-driven components). Instead of programmed, software components are trained by example to get the expected results.
MAIF is developed in Java 5 (especially Generics) and aims at building AI algorithms, by concentrating onto the mapping of real-world problems, while abstracting from their inner working. It can be extended with new algorithms and problem representations.
Hippal is an integrating GUI-framework for a multimodular symbolic A.I.-system IPAL, which combines A.I. Planning, Inductive Program Synthesis, Analogical Reasoning and Learning.
Hippal is client-/server-based and uses the Lili Lisp Interpreter as Centr
A small but extensible Java based "embedded lisp"- derives from the 1960 Mc Carthy Lisp a new consequently functional, dynamically scoped dialect enriched by modern features (pattern matching, parallel processing, implicit lex. closures etc).
This is a framework to develop Contexts and Agents and a Container to run them. The Container lets each Agent interact with the Context and other Agents. The agents are deployed in jar files and each one runs in an exclusive sandbox.
The DataTime Process Framework is intended to support the processing of time-based data in a modular, concurrent, distributed and extensible manner. C++, using YARP, ACE, Qt and MUSCLE on Linux, OSX, Windows and Solaris.
GameBots# is a client API written in C# for GameBots, a research-oriented platform for building artificially-intelligent autonomous agents for computer games.
A java framework for developing meta-heuristics that supports the use of grids environments. The meta-heuristics planned to be realeased are GAs, VNS and NNs. The grid middleware that will be firstly explored is the OurGrid solution.
Mutli-Agent Communicating System.Based on an experiment carried out in the field of the videogame in the artificial intelligence,I board which been able to retain certain lesson of this work,and I would like to remake a Multi Agent System in Open Source.
Robot Controlling System (RCS) - is a .NET-oriented software group for controlling remote mechanical objects, debuging and programming them by .NET-languages
Plansim is a C++ framework aimed to the development of efficient planner agents based on heuristic forward search, that use discrete event simulators as the model for the agent's environment.
RL++ is an easy to use modular open source library for Reinforcement Learning written in C++. It includes learning algorithms (TD, Sarsa, Q) as well as the implementation of value function representations (LookupTable, TileCoding, Neuronal Network).