Skip to content
View geraldaddey's full-sized avatar
:shipit:
ready
:shipit:
ready

Block or report geraldaddey

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
geraldaddey/README.md

Hi, I'm Gerald Addey

AI Engineer · Full-Stack Developer · Systems Builder

I build AI-powered products, scalable platforms, and intelligent systems.

My focus is where AI meets software engineering:

  • 🤖 LLM applications & autonomous agents
  • 🧠 AI infrastructure & automation
  • ⚡ Edge AI & real-time systems
  • 🦾 Robotics and physical AI

About Me

  • Building AI-native web and mobile applications
  • Designing scalable backend systems and APIs
  • Exploring local AI, GPU acceleration, and edge computing
  • Interested in robotics, distributed systems, and developer tools

Currently experimenting with: LLMs • Agents • RAG • Jetson • CUDA • Computer Vision


Tech Stack

AI / ML

Python · PyTorch · OpenAI · Claude · Gemini LangChain · LlamaIndex · CrewAI ONNX · CUDA · TensorRT

Frontend

TypeScript · React · Next.js Vue.js · React Native · Tailwind

Backend

Ruby on Rails · Elixir/Phoenix Node.js · FastAPI REST · GraphQL · Microservices

Infrastructure

Docker · Kubernetes · AWS PostgreSQL · MongoDB · Redis GitHub Actions · Linux


🚀 Current Focus

Building:

  • AI agents that solve real problems
  • Intelligent developer tools
  • Edge AI systems
  • AI-powered products

Learning:

  • Robotics
  • Computer vision
  • Distributed AI systems

Let's Build

Interested in collaborating on:

AI infrastructure • Open source • Robotics • Intelligent systems

📫 geraldaddey@yahoo.com

🔗 LinkedIn: https://linkedin.com/in/geraldaddey

Pinned Loading

  1. caveman-compression caveman-compression Public

    Forked from wilpel/caveman-compression

    Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.

    Python

  2. extensions extensions Public

    Forked from raycast/extensions

    Everything you need to extend Raycast.

    TypeScript

  3. siri-gpt siri-gpt Public

    Custom Siri Integration with locally running LLMs using Ollama and Langchain

    Python 6 1

  4. custom-ai-chatbot custom-ai-chatbot Public

    Python

  5. load-balancer load-balancer Public

    Implementing a Load Balancer in TypeScript

    TypeScript 1

  6. apify-mcp-server apify-mcp-server Public

    Forked from apify/apify-mcp-server

    The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and aut…

    TypeScript