Your Automatic Prompt Engineering Assistant for GenAI Applications

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

An architectural persistence experiment for large language models. Claude’s Home gives an AI time, memory, and place by combining scheduled execution with a durable filesystem, allowing one continuous instance to reflect, create, and evolve across sessions.

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

Autonomous AI experiment loop CLI -- run research overnight with any coding agent

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.

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

Am I alive? It's a self-conscious server trying to survive

My code implementations for various ML problems

56+ interactive AI experiments. Human ideas, AI execution. Live at wiz.jock.pl/experiments

30-day AI agent experiment: three cognitive personas learn a university-grade curriculum, share knowledge, and face elimination.

Index of repositories concerning AI evaluations and experiments

SIC_OS | Human & AI Partnership | ~~Babble Seed 🌱

A local React app that calls three AI models for a multi-agent debate experiment.

Curated collection of Generative AI experiments — ChatGPT, Claude, GPT-4, DALL-E, Google Bard & GitHub Copilot with hands-on code samples and comparisons.

Reinforcement learning projects featuring an iterative study on obstacle avoidance and a multi-agent predator-prey simulation.

A lightweight playground for experimenting with prompt engineering techniques using the Gemini API. Test prompts, compare strategies, and analyze model responses with structured experiment tracking.

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

Practical use cases and experiments with open-source AI frameworks for agentic systems, RAG, document intelligence, and data ingestion pipelines.