GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — dgallitelli - Overview

@dgallitelli dgallitelli Follow
More
  • Overview
  • Repositories
  • Projects
  • Packages
  • Stars
@dgallitelli
dgallitelli
Follow
View dgallitelli's full-sized avatar
🌍
The world is mine for the taking.

Davide Gallitelli dgallitelli

🌍
The world is mine for the taking.
Follow
I like to solve problems, and architect solutions to do that. I tend to work in small-medium groups, often taking the leader role assigning tasks to everybody.
51 followers · 31 following
  • Amazon Web Services
  • Singapore 🇸🇬
  • 22:29 (UTC +08:00)
  • http://dgallitelli.github.io/
  • in/dgallitelli

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: Pair Extraordinairex3Achievement: Quickdraw

Organizations

@UGR2015IT
More
  • Overview
  • Repositories
  • Projects
  • Packages
  • Stars
dgallitelli/README.md

Davide Gallitelli

I build production-oriented AI/ML systems and developer tooling on AWS, with a particular focus on Amazon SageMaker AI and agentic applications. I also build practical tools for Pokémon TCG players.

AWS

AI/ML tools and experiments

  • SageMaker AI Agent Plugin — one portable plugin for Codex, Kiro, and Claude Code, consolidating guidance for SDK v3, training, inference, HyperPod, monitoring, and managed warm pools.
  • SageMaker Lab — consolidated experiments and validated findings across LLM training, AutoML, time series, embeddings, and tabular ML.
  • smbench — throughput and latency benchmarking for real-time inference endpoints.
  • Kiro Power for Amazon Bedrock — guidance for model invocation, agents, knowledge bases, guardrails, fine-tuning, prompts, and flows.

Applications and reference architectures

  • Agents from the Web — reference implementation for connecting AI agents to web interfaces with Amazon Bedrock AgentCore.
  • Governed Data Agent — governed data discovery and natural-language-to-SQL using Strands, AWS MCP Server, and AgentCore Runtime.
  • Intelligent Document Processing Starter — hybrid document extraction comparing Claude, Amazon Bedrock Data Automation, and Amazon Textract.
  • Remote MCP on AgentCore — tutorial for deploying MCP servers to Amazon Bedrock AgentCore Runtime.

Browse all AWS repositories

Pokémon TCG tools

  • JP → EN Card Matcher — identify Japanese cards and view their English equivalents or translated text.
  • Asia Deck Builder Assistant — import Limitless/PTCGL deck lists into the official regional deck builder.
  • Deck Analyzer — explore card co-occurrence and deck-building relationships.
  • TCG Live Redeemer — batch-redeem booster codes through a local Chrome session.

Browse all Pokémon repositories

Other work

  • skillsops — governance tooling for agent skills.
  • autoresearchctl — autonomous optimization loops for arbitrary codebases.
  • Latent Thoughts — research notes and technical writing.

Pinned Loading

  1. skillsops skillsops Public

    skillctl — governance platform for agent skills

    Python

  2. autoresearchctl autoresearchctl Public

    Autonomous optimization loops for any codebase — a CLI that generalizes Karpathy's autoresearch pattern

    Python 1

  3. asia-pokemon-card-deck-builder-assistant asia-pokemon-card-deck-builder-assistant Public

    Userscript that imports Limitless/PTCGL deck lists into the official Pokémon TCG Asia deck builder

    JavaScript 1

  4. pokemon-tcg-jp-en-matcher pokemon-tcg-jp-en-matcher Public

    Mobile-first web app that maps Japanese Pokémon TCG cards to English equivalents and translated card text

    Python

Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.

Uh oh!

There was an error while loading. Please reload this page.

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.