Cross-provider AI code review for Claude Code — evidence-based confidence scoring with Codex, Gemini & Claude

Research-grade Self-Correcting RAG agent built with LangGraph that retrieves knowledge, generates answers, evaluates grounding/relevance/completeness, and iteratively self-improves with confidence scoring and memory.

Zero-Noise utilities for safer product research and review signal analysis.

System that aggregates outputs from multiple Large Language Models (GPT-4, Claude-3, custom models) to generate reliable, high-confidence results through consensus-based reasoning evaluation. Demonstrates sophisticated AI orchestration with 92.7% accuracy improvement over single-model.

Open-source LLM evaluation engine with statistical confidence scoring

AI-powered problem solver using dual-AI validation with 88%+ confidence scoring. By Yourox.ai

Hierarchical multi-agent system with confidence-based routing, homeostasis loops, and morphogenetic memory — inspired by Michael Levin's competency research

Backend document processing pipeline using n8n and Gemini AI. Receives files via webhook, extracts structured data, calculates confidence scores and stores results in Supabase and Google Sheets.

Governed knowledge ingestion engine with artifact lineage, confidence evolution, replayable stages, and append-only persistence. Transcript is just the input — output is traceable artifacts.

A modular AI-driven pipeline for cleaning, normalizing, and standardizing large-scale inventory data with automated SKU generation, confidence scoring, and human-in-the-loop validation.