💼 Portfolio
Current Portfolio
Eduardo is currently working on LLM/VLM + RAG systems and end-to-end AI products.
Explore my pinned projects
Neural Audio Theory 🎵
Open-source educational project on the engineering foundations of AI music generation. Learn the theory behind neural audio synthesis and generation.
Check it out →AirLLM for VLM
AirLLM optimizes inference memory usage, enabling you to run large Vision Language Models (VLMs) on memory-constrained GPUs (as low as 4GB VRAM).
Check it out →AutoPromTune
A Python tool that automatically improves user-written prompts by identifying vague terms and replacing them with precise, semantically richer descriptions using LLMs.
Check it out →C-notebook-backend-engine
C-based notebook system that lets you write, execute, and save C code in sequential cells.
Check it out →FEMOG
An open-source, fully parameterized directory for discovering influential GitHub profiles categorized by engineering domain.
Check it out →llm7.io GUI Tool
A self-developed and unofficial frontend to interact with llm7.io API.
Check it out →llm7R
Use powerful Large Language Models (LLMs) directly in your R workflows for data analysis, visualization, and exploratory research.
Check it out →MedGemma Agentic Workflow
A fully parameterized development framework for building autonomous clinical agents and workflows, powered by MedGemma from Hugging Face.
Check it out →Music Creator Agent
AI-powered music creation using LLM7.io agents to generate Suno AI-ready prompts with specialized agents for genre, tone, lyrics, and prompt creation.
Check it out →NEONMIX
A browser-based stem mixing and mastering tool built with TypeScript and the Web Audio API. Mix and master without opening a traditional DAW.
Check it out →SafeID
Open-source web application designed to add robust watermarks to documents directly in the browser. All processing occurs client-side, ensuring complete privacy and data security.
Check it out →Voice-To-Markdown
A voice-controlled Markdown editor with Spanish and English commands and real-time preview using the Web Speech API.
Check it out →