deliberative-ai

MoralStack is a governance and safety layer for LLM applications. It analyzes user requests before generation, evaluates risk and intent, and decides whether the AI should answer normally, answer safely, or refuse. The goal is to make AI systems more auditable, controllable, and reliable in sensitive or regulated contexts.

Implementation of AI autonomous agents (Reactive & Deliberative) navigating complex environments using State-Space Search algorithms and Markov Decision Processes (MDP), built from scratch in Python and Java.

pi coding-agent extension that brings OpenRouter fusion-style multi-model deliberation natively into any pi session. Self-orchestrated pipeline