General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.
Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
Try Free
Build Agents and Models on One Platform
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.
The Unified Search Framework is an HPC tool for conducting search optimization and experiment design on HighPerformanceComputing platforms. USF has been designed for platforms containing thousands of processors, and tested to 10,000 CPU cores.
The CodeTime platform covers every aspect of parallel software from authoring, through distribution, to run-time. Its goals are: high programmer productivity; write once, run highperformance anywhere; and wide acceptance.
JOST is highperformance JSON Parser and Generator written in C++ and relying on the BOOST Library. The current version is also being extended with a highperformance caching service for JSON objects.
A highly modular client remote/web services library written in Python supporting multiple protocols and transports through a unified interface. All modules are as independent as possible from each other to ensure high re-usability.
If you need a service like heartbeat for linux on a windows machine and the enterprise cluster functionality is too complex, too expansive or you just don't want a quorum. The objective for this application his high aviability.
ZooKeeper is a high available and reliable coordination system. We have moved to Apache. Please go to our new project page at http://hadoop.apache.org/zookeeper/
mpiGraph is designed to inspect the health and scalability of a high-performance interconnect while under heavy load. This is useful to detect hardware and software problems in a system, such as slow nodes, links, switches, or routing contention.
Gold is an accounting system that tracks and manages resource usage on HighPerformance Computers. It acts much like a bank resource credits are deposited into accounts. As HPC resources are used, credits are charged to the appropriate account.
Self Organization of an adaptive learning framework for pervasive graph structures from grids, utilities to semantic governance. Business, performance and provisioning assurance are converged with EGA, ITIL, eTOM,SOX, HIPPA, CobiT and AC
OpenESM project to promote software development of enterprise systems management. Focus areas are (Performance and Availability, Configuration Management, Data Warehousing, Reporting and Correlation).
GRIDportal is a web-based application portal for HighPerformanceComputing. It facilitates easier access to GRID applications through a comfortable web interface. It was designed for use with NorduGrid, but is very generic by nature.
RangeSim is a collection of classes for simulating distributed protocols for range search on P2P (peer-to-peer) network environments. It is based upon the PeerSim simulator, which offers easy configuration, extendability and highperformance.
The aim of our project is to create a portable microkernel and a set of OS services that allow good local performance, multiple concurrent operative system personalities (ie UNIX and a native interface) and easy integration of distributed components.
XenDistro: specialized system for the domain0 of Xen systems. Based on Trustix Secure Linux, it delivers automatic creation of domUs, multiple high-end features like MPIO, EVMS and HA-Linux. Aimed for LSB and CGL compliance, it resides on a 512MB NVRAM.
Brain Net. A Distributed Search Engine Network. Aims to be a scalable distributed search engine allowing dynamic connection of nodes. Performance depends on bandwidth.
A light weigth highperformance cluster server to link several Java machines into one logical unit. Medusa does not compete with J2EE servers but allows clustering of standard Java code for fail-over, redundancy and processing power.
Xen is a virtual machine monitor for x86 that supports execution of multiple guest operating systems with unprecedented levels of performance and resource isolation. Linux 2.4, 2.6 and NetBSD 2.0 ports are available. FreeBSD, Plan 9 ports on the way.
VL-1 is HighPerformanceComputing Middleware designed for the domain experts/researchers/Teachers who want to focus more on their problem then finding out ways of how to implement their problem.
The Sino Project is an Open Source initiative that utilized
code developed by the Chinese government. Sino Linux Middleware v3.0 and Mobile Business Application Suites are built and tested in conjunction with the OSDL in a high volume, enterprise read