
Designs a tailored multi-product agentic data science architecture on Google Cloud that incorporates opinionated best practices
- Open source
- 24.4K GitHub stars
- Cloud and infrastructure

Designs a tailored multi-product agentic data science architecture on Google Cloud that incorporates opinionated best practices

Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache

Interactively discovers requirements and designs holistic, multi-product system architectures, solution blueprints, and deployment recommend

Designs, builds, and deploys AI agents or multi-agent systems on Google Cloud

Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using g

Discovers requirements and generates architectural, design, and deployment guidance for dynamic hybrid search systems by combining semantic

Designs, deploys, and secures Google Cloud Agent Gateway solutions

Assists in designing and implementing secure n-tier serverless web applications and microservices on Google Cloud

Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable ente

Stores, retrieves, and manages data as objects in Cloud Storage on Google Cloud (also known colloquially as GCS) buckets

Creates Cloud Storage on Google Cloud (also known colloquially as GCS) buckets

Troubleshoots and diagnoses Cloud Storage on Google Cloud (also known colloquially as GCS) access and permission denials (403 Permission Den

Mounts Cloud Storage buckets on Google Cloud as a POSIX file system with Cloud Storage FUSE (gcsfuse)

Evaluates Google Cloud workloads for cost efficiency and FinOps alignment using the Google Cloud Well-Architected Framework Cost Optimizatio

Generates operational guidance for CI/CD deployment pipelines, observability, monitoring, logging, and incident management on Google Cloud b

Generates performance-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Performance Opti

Evaluates, designs, and improves the reliability, resilience, availability, fault tolerance, and disaster recovery (DR) of Google Cloud work

Evaluates Google Cloud workloads and provides actionable recommendations for identity management, access control, permissions and roles, net

Provides recommendations for environmental sustainability, carbon footprint reduction, and energy efficiency based on the Sustainability pil

Run a cloud-trial acceptance test on a GPU cluster and write a dated report

Read the local AWS profile, region and caller identity before touching an AWS account

Create an isolated Python 3.12 virtual environment with current boto3 for SageMaker work

Plan a model deployment to Amazon SageMaker and pick the right inference pathway

Find or create a least-privilege SageMaker execution role before deploying

Deploy SageMaker endpoints with autoscaling, alarms, tags and smoke tests built in

Choose the right SageMaker serving container and current image URI for a model

Fine-tune LLMs with TRL or Unsloth on Hugging Face Jobs GPUs and convert to GGUF

Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows acro

Discover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security

Get a Cloudflare Workers app to a working local request by connecting its bindings, secrets, and initial data, then verifying real applicati