Karl Weinmeister

Multimodal AI appraisal using Gemini

Sample application to demonstrate Google ADK and A2A interoperability. For informational purposes only.

MCP server for converting JSON ↔ TOON to reduce LLM token usage.

No description provided.

Catalog of architectural patterns for building AI agents with Google ADK and Gemini

Write browser tests in natural language, built on pytest and allure.

ONNX-based LLM inference server

A model router that dynamically routes queries to the best Gemini model for the job, based on semantic meaning.

No description provided.

Jupyter notebooks for learning and demonstrations

A RESTful API for managing car data, built with Hono, TypeScript, and Google Firestore.

Example Rust Axum application demonstrating deployment to Google Cloud Run and integration with Google Cloud services

No description provided.

Demo application for Google Cloud DevOps scenarios

Serverless execution of autoresearch on Google Cloud

Full-stack Dart application with a Flutter Web frontend and Dart Shelf backend

An MCP server with high-performance text diffing tools, powered by Rust.

No description provided.

Terraform module to deploy vLLM on GKE for high-performance LLM inference. Supports speculative decoding.

Natural language to text agent built with Google's Python ADK

Calculate text perplexity using local language models

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

No description provided.

Deploy a multizone Java application

Node.js samples for Google Cloud Platform products.

Guidelines on writing effective Google Cloud samples.

Sample code and notebooks for Vertex AI, the end-to-end machine learning platform on Google Cloud

A Python SDK for Vertex AI, a fully managed, end-to-end platform for data science and machine learning.

Official Repo for Google Cloud AI Platform

Apps Script samples for Google Workspace products.