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.
TextMarker is now developed and hosted at Apache UIMA (http://uima.apache.org/textmarker.html). TextMarker is a UIMA-based tool for information extraction and more. The full featured editor of the rule language and the build process of UIMA descriptors are complemented with components for visualization, explanation, testing and rule learning.
Palamedes is a plugin that enables users to use Eclipse for Game Description Language (GDL) development, making Eclipse a first class GDL IDE. It comes with many goodies such as syntax highlighting, knowledge base analysis, debug and many other.
iGROM helps you with developing programs in languages such as DLV or smodels. Can be used either as stand-alone or as a plugin to Eclipse. You can also extend it to other similar languages by only writing a parser and several support classes.
...It suports automatica detection of next engines to be installed
- cuneiform with its languages
- tesseract with language database files
- gocr
Supports
- adding custom engines
- bach processing of images
- text postprocessing
Yet another python powered bot for the browsergame "Travian".
We want to make this bot more effective then any human, at construction defensing and farming.
VINE is a vocabulary Integration Environment Tool, developed at MMI. It allows to create fast mappings and alignments from ontologies in OWL. VOC2OWL is a tool to create ontologies from ASCII files. They are both JAVA based and are delivered as a Rich Cl
WSMO Studio is a Semantic Web Service and Semantic Business Process modelling environment based on the Web Services Modelling Ontology (WSMO). WSMO Studio is available as a set of Eclipse plug-ins that can be extended and customised by 3rd parties.
A Perl/Tk graphical expert system shell. Uses AI::ExpertSystem::Simple and a custom knowledge base language (with included syntax-highlighting editor). Allows extension functions to be quickly and easily written in Perl.
This project about providing run-time support for developing Decentralized Autonomic Computing systems (Eclipse Innovation Grand). Currently the project contains a automatic guided vehicle (AGV) simulator and an editor and visualisation as eclipse plugin
Joshi is a program that tries to recognize shapes on an image with a focus on OCR. It converts the image to vector graphics (polylines) and then tries to project these on stored vector graphics, calculating the best match.
The JSGF Editor supports development of grammars for speech recognition with the Java Speech Grammar Format. It is provided as a plugin for Eclipse 3.* (tested on 3.1 and 3.2)
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.
SenseRank Sys:
- builds the dictionaries (multidim matrices) of words’ values;
- for the set utterance in certain language builds a figure in multidimensional space (in the matrix space) of values (visual schema), which is topological view of sense
Prenzl!! is a desktop application and a screen saver running artistic cellular automata. The application is based on an Eclipse architecture and the rules can be in native. Our mission is to provide a viewer and an SDK for this kind of art, called CArt.
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.
The OpenCV DLLCapture project goal is to provide an easy way for using the Intel OpenCV library face recognition feature within custom built applications.
This is RoboCup player. The player can be used with soccer server system (http://sserver.sourceforge.net). It can be used as a library for your custom player or can be programmed with build-in scripting language (very simple).
Galileo is a library for developing custom distributed genetic algorithms developed in Python. It provides a robust set of objects that can be used directly or as the basis of derived objects. Its modularity makes it easy to extend the functionality. The
A DAML+OIL ontology editor with constraint propagation functionality to ensure that constraints applied to properties and restrictions are correctly propagated through an ontology, and datatype management functionality for manipulating custom datatypes.
Prolix is a "binary bot" chat interface
and bot for various battle.net(tm) like
services such as bnetd, fsgs, and possibly
battle.net itself. Prolix offers a modular
design allowing one to create and use
custom controls, bots and displays.
Karlsruhe Service Management Architecture (KASMA): KASMA is a new framework for the next generation Web services developed by Research Center for Computer Science, University of Karlsruhe.
This project is intended to become an advanced software tool which will allocate resources for projects described by Gantt charts and rules, it also will try to create plans and schedules, based on templates, rules and historical information.
Custom BLEURT model for evaluating text similarity using PyTorch
...The model predicts a score indicating how similar a candidate sentence is to a reference sentence, with higher scores indicating greater semantic overlap. Unlike standard BLEURT models from TensorFlow, this version is built from a custom PyTorch transformer library. It requires installing the model-specific library from GitHub to function properly. Once set up, it can be used to compute similarity scores with minimal code. BLEURT-20-D12 enables more flexible deployment in PyTorch-based workflows for evaluating language generation outputs.