Improve scientific collaboration in AI-assisted research. Citation validation, claim verification, cross-file consistency.

A personal learning environment that helps you find your unknown unknowns by grilling you against the consensus research on a particular topic or question.

This repository contains a solutions for the exercises in the "Math Concepts For Developers" course at SoftUni .

97 reasoning patterns from history's greatest minds — as Claude Code agents. Curie to Toulmin. Engineering to humanities. Every claim cites its source. Every commit is checked. The only agent system where "I don't know" is a feature.

Structured observation management for research agents

Please fork and criticize!

Scientific TDD for AI coding agents: pre-registration before data, claims audit before submission, external novelty gate, reproducibility. Claude Code + 4 platforms.

ASRP (AI Scientific Research Platform) Desktop — Multi-Agent collaborative scientific research platform

MCP server for Claude Desktop that applies Popperian falsifiability to verify claims from social media, news and blogs — with real academic sources, not opinions.

Desktop app built with Flutter to simulate solar PV array energy assessment using the OSM-MEPS model at fixed tilt-azimuth orientations (check the releases sidebar/tab).

A conservation-honest diagnostic framework for auditing early-universe models and separating physical dynamics from descriptive bookkeeping.

Prediction-error optimization. The agent guesses before each experiment. Wrong predictions are the learning signal. One file, zero dependencies. pip install theorist

Axiomatic Inference Engine — controlled experiments validating two separable mechanisms: structural depth (TOPO) and immune-driven edge density (Q). | Axiomatikus következtető motor — kontroll-kísérletek két szétválasztott mechanizmus megerősítésére: TOPO ← struktúra, Q ← immunrendszer.

Notes for the Anleitung zum wissenschaftlichen Arbeiten (scientific writing) course at HdM Stuttgart.

railroad industry and manufacturing

Introduction in the scientific method using the Hertzsprung-Russel-Diagram

What if the AI agent guessed first? 251 experiments. The predicting agent adapted to a 5x compute shift on try one. The reflecting agent took 7. The searching agent never caught up.

Experimental Methodology at Royal Institute of Technology KTH

A logic engine and persona bootloader for LLMs (validated on Gemini 3) designed to bypass consensus bias through rigorous inquiry. Using a 4-Axiom hierarchy (Data, Scope, Mechanism, Probability), it enables human-AI symbiosis to preserve persistent logic across sessions.

Learning material on the scientific method for security research