arin-deloatch/docta
A project about tracking differences across documentation versions
AI Engineering @ Red Hat
A project about tracking differences across documentation versions
LLM tooling stack
A recursive execution runtime for software engineering tasks, where coding agents are interchangeable executors and recursion is the primary computation model.
A high-throughput and memory-efficient inference and serving engine for LLMs
Centralized configuration for Claude agents and skills, enabling reusable, version-controlled definitions of agent behavior, tool usage and reasoning patterns across projects.
Source code for our custom providers.
watching repos
pydantic ai spike
Self-improving AI agent research spike using Pydantic AI
Config files for my GitHub profile.
Cerberus is a lightweight pipeline for filtering, normalizing and ingesting documents into RAG systems. It focuses on the “gatekeeper” step of the pipeline: making sure only high-quality, relevant, and deduplicated documents get chunked, embedded, and stored in your vector database.
PoC for MCP evaluation using DeepEval
:crab: Small exercises to get you used to reading and writing Rust code!
This repository is my personal sandbox for learning and experimenting with the Rust programming language 🦀.
A machine learning project to predict employee attrition using historical HR data. The model analyzes key factors such as job satisfaction, performance, and compensation to identify employees at risk of leaving, helping organizations take proactive retention measures.
This project utilizes the Census Income dataset from the UCI Machine Learning Repository to perform an end-to-end statistical analysis. Using Python 3.11 and popular data manipulation, visualization, and statistical libraries, we demonstrate how to process, analyze, and visualize the dataset. The project focuses on cleaning data, feature selection,
This project focuses on the early detection and management of diabetes using machine learning. By analyzing a comprehensive dataset of health metrics, our predictive model identifies individuals at risk for diabetes onset, enabling healthcare providers to take proactive measures and improve patient outcomes.
This project leverages Natural Language Processing (NLP) techniques and machine learning algorithms to predict drug ratings based on patient reviews. By analyzing a dataset of drug reviews from the UCI Machine Learning Repository, the goal is to accurately forecast a drug’s rating (out of 10) based on the content of the review.
The primary objective of this project is to develop a deep learning model that can predict the composer of a given musical score accurately. The project aims to accomplish this objective by using two deep learning techniques: Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN).
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all