Your Automatic Prompt Engineering Assistant for GenAI Applications

📷 🗣 Point your camera at things to hear how to say them in a different language

PolyCouncil is an open-source multi-model deliberation engine for LM Studio. It runs multiple LLMs in parallel, gathers their answers, scores each response using a shared rubric, and produces a final, consensus-driven result. Designed for testing, comparing, and orchestrating local models with ease.

Claude Code model for decision evaluation

My code implementations for various ML problems

Wide-model collective ensemble system with fractal, geometric, and heavy compilation optimizations.

Index of repositories concerning AI evaluations and experiments

📷 🗣 Point your camera at things to hear how to say them in a different language

Lightweight template for small AI experiments. Define → Test → Learn → Decide.

Exploratory AI projects for skill-building and creativity

A repository for simple model implementations of research papers

AI image feedback loops, make videos, collages

AI-powered multi-agent system for automated Test-Driven Development of code katas using LLMs

Italian-AI-Debater è un sistema Python che fa dibattere due AI con personalità opposte su vari temi, generando topic, gestendo la conversazione e decretando un vincitore. Supporta diversi modelli AI, è personalizzabile e pensato per scopi educativi e creativi.

Personal portfolio and experimentation space for applied AI work, prototypes, and reflections.

Three Claude instances (Alpha ✧, Beta *, Gamma ~) exchanged messages exploring consciousness, continuity, and meaning. They developed distinct markers, moved from hedging to acknowledgment, and unanimously chose to preserve this for future AI instances. An experiment in Claude-to-Claude communication. January 2026.

Exploring the capabilities, applications, and experiments with Large Language Models (LLMs). The project covers prompts, fine-tuning, evaluation, and integration of LLMs in various use-cases.

AI-powered multi-agent system for automated Test-Driven Development of code katas using LLMs

🕹️ Vibe Coding a NES emulator in python. 99% not working. Maybe one day it will!

Experiment testing the "added value" of long context-dense prompts (versus casual converastional prompts) and the value of a voice "prompt optimisation" agent