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 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.
Container for robot/environment simulation. The container simulates an environment, and gives to the robots living in it access to sensor views.
The goal of this project is to provide the open source community a tool for robot behavior test and challeng
A Java based simulation of the MIC1 architecture as described by Andrew S. Tanenbaum in his book Structured Computer organization. In addition a model for interaction with a HD, screen and keyboard are provided.
BabyTALK is to add another brick in the wall of natural languages learning. The baby needs to structure a corpus of texts when his tutor points and talks about a particular part of the corpus. The baby is also to describe any selected part of the corpus.
The Text Annotation Environment (tae) can be used to annotate natural language text manually or automatically (UIMA Annotator) with meta information (tokens, part-of-speech, named entities, ...). Tae is based on Eclipse and IBM's UIMA.
KNN-WEKA provides a implementation of the K-nearest neighbour algorithm for Weka. Weka is a collection of machine learning algorithms for data mining tasks. For more information on Weka, see http://www.cs.waikato.ac.nz/ml/weka/.
CRFChunker: Conditional Random Fields Phrase Chunker (Phrase Chunking Tool) for English. The model was trained on sections 01..24 of WSJ corpus and using section 00 as the development test set (F1-score of 95.77). Chunking speed: 700 sentences/s
CRFTagger: Conditional Random Fields Part-of-Speech (POS) Tagger for English. The model was trained on sections 01..24 of WSJ corpus and using section 00 as the development test set (accuracy of 97.00%). Tagging speed: 500 sentences/s.
DrPangloss is a python implementation of a three operator genetic algorithm, complete with a java swing GUI for running the GA and visualising performance, generation by generation
The Rule Based Service Level Agreement (RBSLA) project focuses on knowledge representation concepts for service level management of IT services. At the core are rule-based languages to describe contracts and service level agreements in a formal way.
mlearn is a gradient based learning toolbox for matlab. While it is fairly simple to build a neural network, it is designed for ease of implementing new kind of gradient based architecture.
mRDP (Multicast Resource Discovery Protocol) API is a Java API that enables RDF resource discovery via SPARQL queries over UDP multicast messages. The mRDP API uses the Jena API for managing the RDF graph and SPARQL queries execution.
JIMO(Java-based Instant Messenger One), supports multiple protocols via services, including AIM, MSN, Yahoo, IRC. It is flexible through its plugin architecture, with an intelligent agent, Chatbot.
Agent based model of organizations considering the interplay between the formal hierarchical structure and the process network emerging while the organization performs a task-set.
An implementation of the Compositional Pattern Producing Networks (CPPNs) and Neuro-Evolution of Augmenting Topologies (NEAT) proposed by Kenneth O. Stanley, based on the Genetic Art tool from Mattias Fagerlund.
An open simulation of the casino game "let it ride" written in Java. Runs AI agents that play the came and statistically tracks their success. Also has a command-line interface for playing the game.
This project will provide an interface for using Lightweight Communications Calculus (LCC) to control agents in the Unreal Tournament enviroment. It consists of a prolog-style interperter, LCC parser/IDE,a GUI / LCC editor and interfaces to the Gamebots
Performs summarization, categorization, key phrase generation,full text indexing and search,part of speech tagging,identification of place and human names in various document format. Latest code is available at http://www.twit88.com/
This project intends to create an indexing search engine, for knowledge management. The primary object is to apply an information retrieval core. And implement a knowledge data discovery theory such as data mining algorithm, text mining.
URBI: Universal Robotic Body Interface. URBI is a scripted command language used to control robots (AIBO, pioneer,...). It is a robot-independant API based on a client/server architecture. Liburbi C++/Java/Matlab are available here. Forum available at ht
Molle is a cross-platform prover for modal logic, which exploits the modal semantic tableaux method. It features a very usable graphical interface, with interactive representation of generated models. Molle is maintained by Politecnico di Milano.