NVIDIA L4 GPUs. 5-second cold starts. Scale to zero when idle.
Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
Try Free
$300 Free Credits for Your Google Cloud Projects
Start building on Google Cloud with $300 in free credits. No commitment, no credit card required until you're ready to scale.
Launch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
TOFFEE-DataCenter is the new TOFFEE variant meant for Data-Center, Server, HPC, Load Balancing, Cluster/Cloud Computing and SDN deployments. With TOFFEE-DataCenter (and or TOFFEE), OEMs and other equipment vendors can make use of this platform/stack, integrate, port and build WAN Optimization devices/appliances on to their existing product range. Or build a dedicated WAN Optimization hardware product series via the same.
openlsm - Web based open source, Linux Server Management(LSM) -LAMP ,FTP,Jabber, Samba,NFS,LDAP and MySQL based virtual hosting, Squid,Backup,Quota,Mail ,spam-assassin, mailable,Asterisk, web hosting, Load balancing, nagios and ganglia monitoring.
Git repo: https://github.com/asipto/siremis
Web management interface for Kamailio (OpenSER) - handle subscriber profiles, access control lists, accounting, least cost routing and load balancing, monitoring charts, xmlrpc communication with SIP server
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.
An implementation of a MUD using Java and SQL. It will be fully portable to any JVM, and store the whole MUD in a relational database. Allowing for load balancing and multi server environments and plugins.