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

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

Structured observation management for research agents

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.

Please fork and criticize!

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.

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

railroad industry and manufacturing

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

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

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.

Experimental Methodology at Royal Institute of Technology KTH

Epistemic method visibility project. Reduce cognitive stagnation. Promote self-doubt across positions. Pro-method, not pro-science.

Learning material on the scientific method for security research

A research protocol for falsifiable multi-agent inquiry that prevents confirmation bias through role separation, sequence enforcement, and pre-committed falsification criteria (PACI).

Theorem of the Unnameable [⧉/⧉ₛ] — Epistemological framework for binary information classification (Fixed Point/Fluctuating Point). Application to LLMs via 3-6-9 anti-loop matrix. Empirical validation: 5 models, 73% savings, zero hallucination on marked zones.