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.
UnityCA is a Certificate Authority "front end" based on the Community-Oriented CA (COCA) model, which was primarily developed for non-profit "free CAs." Organizational and end-user interfaces provide trusted web management of the installed CA (eg ElyCA).
The Job Jar is a simple batch queuing system for Unix. Its main
distinguishing feature is that there is no central daemon. Instead, an
arbitrary set of workers cooperatively claim jobs from a central
directory. A job is any Unix executable file.
MPY is an MPI implementation for Python using MPICH (or any other MPI implementation). MPY also provides helper functions for ease of programming, and a simple plug-in interface.
AppSignal's MCP server hands Claude, Cursor, or Zed your real errors, traces, and the deploy that shipped them. AI writes the fix; you review the diff.
Healthcare Xchange Protocol for interoperative communications. Data exchange/transfer, platform independent,XML-RPC, HL7, SOAP, EDIFACT, simple,easy, authenticated, secure, transparent, no geo-restrictions, open sourced, peer reviewed, collab development
pyChelsea is a python based, personal, visited, web page indexer, seach engine and interface for the browser/platform of your choice. If you remember a page based on a phrase, pyChelsea is for you.
Project VDW serves as a repository for all things pertaining to Van Der Waerden sequences. Volunteers to run the distributed client, mathematicians to help with theory, and anyone interested in VDW sequences are welcome!
Pythońol is an all-in-one program to help English speakers learn Spanish. Features include: Pronunciation, verb conjugation, dictionary (70,000+ words), thesaurus, quizzes, full-text translation, idioms, a verb browser, and a large reference section.
J-Sim (previously known as JavaSim) is a component-based, compositional simulation environment written in Java. It is built upon the autonomous component architecture (ACA), a component architecture at the implementation level.
SystemSpecifyer is used to develop and maintain complex, well structured, systems specifications, in normal language. Using the System Matrix double matrix relation building mechanism specs can be tested for completeness, correctness and consistency.
Xapian is a Search Engine Library, written in C++ with bindings for Perl, Python, PHP, Java, Tcl, C# and Ruby. Xapian allows you to easily add advanced indexing and search facilities to your applications. See www.xapian.org for more information.
MAF (Mobile Agent Framework) is a research prototype which aims to facilitate the development and evaluation of mobile agent by providing a set of handy primitatives and simulation tools.
A benchmarking utility providing administration of the benchmarking procedure and a web interface for public access on the results. The goal is to have an automated procedure after the benchmark specification.
We propose a userspace Process Classifier based on SELinux Security_context(PCSS).PCSS use SELinux security context to classify the processes in different categories which is useful for process grouping systems like CKRM,Cpuset,ELSA,Containrs etc.
SuperG is a code library written in Python intended to quickly enable programmers in a scientific environment to manage data files created by dispersed scientific instrumentation.
Multi-AI workspace with persistent cross-session memory via MCP
SynquoRum is a multi-AI workspace for people who use multiple language models daily and are tired of fragmented context when switching tools.
Most AI products treat memory as belonging to the model. Every new session starts from zero. SynquoRum inverts this: memory belongs to the workspace, not to any specific agent. Through an MCP (Model Context Protocol) server with 22 tools, the workspace exposes its memory to any MCP-compatible client — Claude.ai, Cursor, Cline, custom agents — so the...
A semantic memory software tool “reflects” one's “imagination”. In it, arbitrary concepts may be described, stored, arranged, transformed, and shared. One may verbalize thoughts as they arise in the mind to externalize and digitize “mental obj