Back to home

Aloy Studio

Project and work I am involved in

Personal Website

March 2024

My portfolio website built with Next.js, TypeScript, and Tailwind CSS

Next.jsTypeScriptTailwind CSS
N

NewPaper

Feb 2025

Modular, unopinionated team and project management platform for managing people, time, and work. Integrated tools for team management, time tracking, tasks, reporting, and collaboration—on web and mobile. My role: Full-Stack Engineer—architected and engineered the mobile app for Android and iOS to production using TypeScript, React Native, Kotlin, and Swift; wrote the API with Node.js and deployed to AWS; built native modules.

TypeScriptReact NativeKotlinSwift
U

Utlwa

Feb 2025

Music player for true music lovers: lossless audio, smart playlists, offline listening, and a library for your entire collection. High-fidelity sound, intuitive controls, and a vibrant music community. Available on web, Windows, Mac, Android, and iOS.

A

Aloygrad

Feb 2025

Minimal reverse-mode automatic differentiation engine built to understand differentiable programming and neural networks from first principles, giving engineers full control over how gradients work.

PythonCalculusLinear Algebra

Pori

Feb 2025 - Present

Open-source AI agent framework with human-in-the-loop oversight. Agents follow a structured Plan → Act → Reflect → Evaluate loop with approval gates that pause execution before sensitive operations. Features multi-agent teams (route, broadcast, delegate modes), custom tool registry with Pydantic validation, extensible Letta-style memory, sandboxed execution, and lightweight LLM wrappers replacing LangChain with direct Anthropic/OpenAI SDK integration. Configurable via YAML, runs as CLI or FastAPI server.

PythonFastAPIAnthropicOpenAI

AuditRAG

March 2025

Production-grade Retrieval-Augmented Generation platform. Upload any PDF, chat with it using hybrid search (dense + sparse + RRF fusion), and get cited answers. The system auto-generates evaluation datasets on ingestion, runs quality harnesses (exact match, token F1), and tracks per-query observability — latency percentiles, token usage, and cost. Built with FastAPI, Qdrant, PostgreSQL, and a React + TypeScript frontend. Demonstrates the full RAG lifecycle: ingestion, retrieval, generation, evaluation, and monitoring.

PythonFastAPIQdrantPostgreSQL