Google Cloud Tech
@GoogleCloudTech
Follow along for how-tos, demos, product news, and more.
For company updates, check out @GoogleCloud.
Watch #GoogleCloudNext# on demand ⬇️
1.6K Following 1.3M Followers
The secret to high-performing coding agents isn't just raw reasoning power—it's the 3 connected layers:
🔹 Model
🔹 Harness
🔹 Knowledge
Watch "3 Layers of a High-Performing Agent Stack" with @SmithaKolan to learn more →
Show more
Dataform now integrates with Developer Connect for seamless Git connectivity. Securely access remote repositories in private networks without exposing them to the public internet.
Here's the guide to connect a remote repository using Developer Connect →
Show more
Everyone is talking about agent harnesses, but what exactly is one?
Simply put: AI Agent=LLM+Agent Harness
@lukeschlangen and @smithakolan break it down on the latest episode of The Agent Factory →
Show more
Power your agents: Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enterprise.
Key capabilities include: video avatars, fluid dialogue, tool calling, and more.
Start building today ↓
Show more
Run open models like Gemma 4 completely offline in the Antigravity SDK.
Built on Google AI Edge’s LiteRT, you can now run Gemma 4 directly on your local GPU. Zero API costs, total data privacy, and no internet required.
Show more
Claude Opus 5.5 is on Google Cloud!
Built for everyday complex tasks, it handles long-running coding and knowledge work while reporting back clearly on what it did, what it found, and what it needs next at a lower cost per task.
Try it in Model Garden →
Show more
"I aspire to be an incredibly lazy prompter." —@_lopopolo
Ryan joins The Agent Factory to make the case for not writing any code manually, and break down how harness engineering can help you get there →
Show more
See how artist Leo Villareal used Gemini and Google Antigravity to supercharge his authoring software in the process of bringing his light sculpture to life. "Buckyball" is a celebration of the vibrancy of NYC and debuted this summer.
Show more
Scaling an AI agent fleet?
We provide full-stack agentic solutions, and now we're expanding our portfolio with Filestore agent volumes: fully managed, elastic file storage purpose-built to give agents isolated, economical, high-performance workspaces →
Show more
Class is in session with @NVIDIAAI.
Join @ivnardini and @katjasrz for a hands-on course that walks through the end-to-end journey of building, profiling, and scaling JAX models on NVIDIA GPUs—from initial setup to production serving →
Show more
We’re partnering with @inferact (the team behind @vllm_project) to make TPUs a first-class citizen for open-source AI inference.
Together, we’re delivering:
- Upstreamed open-source TPU kernels
- Native PyTorch integration via TorchTPU
+ so much more ↓
Show more
What questions do you have for Ryan?
Share them below ⬇️
Gemini improves the software development lifecycle (SDLC).
Take this Google Skills course to learn how to develop and build a web application, fix errors, write tests, and query data with help from Gemini →
Show more
If you're using AlloyDB and want a quick way to build an AI agent with your data, use the remote MPC server!
This codelab provides a guide to getting started, enabling it as part of the toolset for an AI agent, and using it as part of an application →
Show more
Google Cloud @googlecloud announced its Day 0 support for Kimi K3 with SGLang! They just published the full guide for serving the 2.8T-param MoE with SGLang on GKE, including DSPARK speculative decoding.
A model this size is an infrastructure problem before it's a model problem. A4 and A4X VMs gave SGLang the memory bandwidth and interconnect to keep K3 fast under real concurrency.
Three ways to deploy: Model Garden, AI Hypercomputer recipes, GKE.
Guide in the comments 👇
Show more
